337 accepted papers
While Diffusion Transformers (DiTs) have revolutionized high-fidelity image synthesis, the prohibitive computational costs of training at ultra-high resolutions necessitate robust inference-time extrapolation. Existing extrapolation methods typically operate under a *scale-agnostic* assumption, trea…
Pipeline inspection is essential for maintaining the safety of critical infrastructure, but manual inspection is dangerous and inefficient, and existing robotic solutions struggle to handle curved and constrained surfaces. Traditional planning methods are either computationally expensive or prone to…
Large language models (LLMs) have demonstrated remarkable capabilities across a variety of domains. However, their applications in cryptography, which serve as a foundational pillar of cybersecurity, remain largely unexplored. To address this gap, we build \textbf{AICrypto}, a comprehensive benchmar…
Visual autoregressive modeling (VAR) via next-scale prediction has emerged as a scalable image generation paradigm. While Key and Value (KV) caching in large language models (LLMs) has been extensively studied, next-scale prediction presents unique challenges, and KV caching design for next-scale ba
Tuning stochastic gradient methods such as stochastic gradient descent (SGD) and stochastic gradient Langevin dynamics (SGLD) for approximate sampling and uncertainty quantification remains challenging, particularly in relevant settings using a large batch size or when the model is misspecified. Exi…
Control barrier functions (CBFs) have proven to be effective for obstacle avoidance in robot teleoperation systems. However, for classical CBF, model uncertainties and external disturbances can significantly degrade the robustness of safety control. Moreover, the fixed safety boundary lacks adaptabi…
Existing evaluations of agents with memory typically assess **memorization** and **action** in isolation. One class of benchmarks evaluates memorization by testing recall of past conversations or text but fails to capture how memory is used to guide future decisions. Another class focuses on agents …
Low-Light Image Enhancement (LLIE) is a challenging task, as severe information loss means a single input can correspond to multiple plausible restorations. This inherent ambiguity causes conventional regression-based models to produce overly-smooth results that lack detail. While recent generative
Noisy correspondence, characterized by mismatches in cross-modal data pairs, presents a significant challenge for real-world applications. Current approaches primarily rely on direct cross-modal pairwise similarity metrics, which suffer from two critical limitations: noise sensitivity, where direct
Multi-LLM systems harness the complementary strengths of diverse Large Language Models, achieving performance and efficiency gains unattainable by a single model. In existing designs, LLMs communicate through text, forcing internal representations to be transformed into output token sequences. This…
Cinematic video production requires control over scene-subject composition and camera movement, but live-action shooting remains costly due to the need for constructing physical sets. To address this, we introduce the task of cinematic video generation with decoupled scene context: given multiple im
During robotic disaster relief missions, state estimation still faces significant challenges, especially when GNSS is denied or sensor perception undergoes degradation. In this paper, we introduce a degradation-aware LiDAR-Thermal-Inertial SLAM, DaLiTI, that leverages the complementary nature of mul…
Road network representation learning (RNRL) has attracted increasing attention from both researchers and practitioners as various spatiotemporal tasks are emerging. Recent advanced methods leverage Graph Neural Networks (GNNs) and contrastive learning to characterize the spatial structure of road se
Recent benchmarks for Large Language Model (LLM) agents primarily focus on evaluating reasoning, planning, and execution capabilities, while another critical component—memory, encompassing how agents memorize, update, and retrieve long-term information—is under-evaluated due to the lack of benchmark…
Existing AI-based film generation systems can generate high-quality videos, but struggle to design expressive camera language and establish cinematic rhythm. This deficiency leads to templated visuals and unengaging narratives. To address these limitations, we introduce FilMaster, an end-to-end auto…
Ego-vision-based navigation in cluttered environments is crucial for mobile systems, particularly agile quadrotors. While learning-based methods have shown promise recently, head-to-head comparisons with cutting-edge optimization-based approaches are scarce, leaving open the question of where and to…
Fracture injuries often lead to complex bone fragmentations, posing significant challenges for accurate segmentation in surgical planning and trauma assessment. Manual annotation of each fragment is time-consuming and inconsistent, while existing automated methods often fail to separate individual f
Text-to-video generation models have shown significant progress in recent years. However, they still struggle with compositional text prompts, such as attribute binding for multiple objects, temporal dynamics associated with differ- ent objects, and interactions between objects. Inspired by ef- fect
Category-agnostic pose estimation (CAPE) aims to localize keypoints on query images from arbitrary categories, using only a few annotated support examples for guidance. Recent approaches either treat keypoints as isolated entities or rely on manually defined skeleton priors, which are costly to anno…
Soft robots are inherently compliant and safe, making them suitable for humaninteractive applications such as surgery. However, their nonlinear and hysteretic behavior poses significant challenges for accurate modeling and control. We present a soft robotic system and propose a hysteresis-aware whol…
Inference time optimization techniques, such as repeated sampling, have significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, the critical role of model uncertainty remains largely underexplored in these optimization strategies. In this paper, we investigate the…
Aerial robots interacting with objects must perform precise, contact-rich maneuvers under uncertainty. In this paper, we study the problem of aerial ball juggling using a quadrotor equipped with a racket, a task that demands accurate timing, stable control, and continuous adaptation. We propose Jugg…
Recent large language models (LLMs) achieve strong performance in generating promising reasoning paths for complex tasks. However, despite powerful generation ability, LLMs remain weak at verifying their own answers, revealing a persistent capability asymmetry between generation and self-verificatio…
Developing Large Language Models (LLMs) to cooperate and compete effectively within multi-agent systems (MASs) is a critical step towards more advanced intelligence. While reinforcement learning (RL) has proven effective for enhancing reasoning in single-agent tasks, its extension to multi-turn, mul…
Medical language models face critical barriers to real-world clinical reasoning applications. However, mainstream efforts, which fall short in task coverage, lack fine-grained supervision for intermediate reasoning steps, and rely on proprietary systems, are still far from a versatile, credible and
Adapting large language models (LLMs) to low-resource domains remains challenging due to the scarcity of domain-specific data. While in-domain data is limited, there exists a vast amount of general-domain data that shares similar question–answer formats and reasoning patterns with domain tasks. This…
Discrete diffusion language models (dLLMs) have recently emerged as a promising alternative to traditional autoregressive approaches, offering the flexibility to generate tokens in arbitrary orders and the potential of parallel decoding. However, existing heuristic sampling strategies remain ineffic…
Neural Network k-Nearest Neighbor (NN-kNN) was proposed as an interpretable network model that learns feature weights and similarity to retrieve relevant cases for classification. This paper extends it to regression with the goal of generating accurate predictions based on neighboring cases with sim
One central challenge in Neural Combinatorial Optimization (NCO) is handling hard constraints efficiently. Beyond the two classic paradigms, i.e., Local Construction (LC), which sequentially builds feasible solutions but scales poorly, and Global Prediction (GP), which produces one-shot heatmaps yet…
Subgraph matching, a cornerstone of relational pattern detection in domains ranging from biochemical systems to social network analysis, faces significant computational challenges due to the dramatically growing search space. Existing methods address this problem within a filtering-ordering-enumerat
Accurate motion control in the face of disturbances within complex environments remains a major challenge in robotics. Classical model-based approaches often struggle with nonlinearities and unstructured disturbances, while reinforcement learning (RL)-based methods can be fragile when encountering u…
The stochastic minimax optimization problem has widespread applications in machine learning. Recently, numerous distributed minimax optimization algorithms have been developed to handle distributed training data. However, most of these algorithms suffer from high communication costs. To address this…
Multi-UAV pursuit-evasion, where pursuers aim to capture evaders, poses a key challenge for UAV swarm intelligence. Multi-agent reinforcement learning (MARL) has demonstrated potential in modeling cooperative behaviors, but most RL-based approaches remain constrained to simplified simulations with l…
While large reasoning models trained with critic-free reinforcement learning and verifiable rewards (RLVR) represent the state-of-the-art, their practical utility is hampered by ``overthinking'', a critical issue where models generate excessively long reasoning paths without any performance benefit.…
Recently, significant progress has been made in developing reasoning-capable Large Language Models (LLMs) through long Chain-of-Thought (CoT) techniques. However, this long-CoT reasoning process imposes substantial memory overhead due to the large Key-Value (KV) Cache memory overhead. Post-training…
Recent advances in vision-language-action (VLA) models have motivated the extension of their capabilities to embodied settings, where reinforcement learning (RL) offers a principled way to optimize task success through interaction. However, existing methods remain fragmented, lacking both a unified …
Reward modeling is essential for aligning large language models with human preferences through reinforcement learning. To provide accurate reward signals, a reward model (RM) should stimulate deep thinking and conduct interpretable reasoning before assigning a score or a judgment. Inspired by recent…
Macro placement is a crucial subproblem of chip design, focusing on determining the locations of numerous macros while minimizing multiple metrics. In recent years, reinforcement learning (RL) has gained traction as a favorable technique to improve placement performance. However, existing RL-based p
Class-Incremental Learning (CIL) aims to develop models to continuously learn new classes without forgetting learned old ones. Recent advances combine pre-trained models with parameter-efficient fine-tuning, achieving promising results. However, these approaches typically allocate new trainable para
Large language models (LLMs) are pretrained on corpora containing trillions of tokens and, therefore, inevitably memorize sensitive information. Locate-then-edit methods, as a mainstream paradigm of model editing, offer a promising solution by modifying model parameters without retraining. However, …
Standard human preference-based alignment methods, such as Reinforcement Learning from Human Feedback (RLHF), are a cornerstone technology for aligning Large Language Models (LLMs) with human values. However, these methods are all underpinned by a strong assumption that the collected preference data…
In environments where robots operate with limited global navigation satellite system accessibility, ultra-wideband (UWB) localization technology is a popular auxiliary solution to assist visual–inertial odometry systems. However, current UWB approaches lack 3-D pairwise localization capability and s…
Training expressive flow-based policies with off-policy reinforcement learning is notoriously unstable due to gradient pathologies in the multi-step action sampling process. We trace this instability to a fundamental connection: the flow rollout is algebraically equivalent to a residual recurrent co…
Vision-Language-Action (VLA) models have emerged as a powerful paradigm for robotic manipulation. Despite substantial progress enabled by large-scale pretraining and supervised fine-tuning (SFT), these models face two fundamental challenges: (i) the scarcity and high cost of large-scale robotic traj…
While scaling laws for imitation learning have primarily focused on generalization in open-world settings, the relationship between data and precision in closed-world tasks like robotic assembly remains largely unexplored. This paper systematically investigates this relationship and introduces a nov…
Improving reasoning abilities of Large Language Models (LLMs), especially under parameter constraints, is crucial for real-world applications. Looped transformers address this by performing multiple latent iterations to refine each token beyond a single forward pass. However, we identify a latent ov…
Class Incremental Learning (CIL) aims to enable models to continually learn new classes while retaining previously learned knowledge. The principal challenge in CIL is catastrophic forgetting, which prior approaches typically address by distilling knowledge from previous model. However, such way is
Reinforcement learning from human feedback (RLHF) has proven effectiveness for aligning text-to-image (T2I) diffusion models with human preferences. Although Direct Preference Optimization (DPO) is widely adopted for its computational efficiency and avoidance of explicit reward modeling, its applica…
As humans increasingly share environments with diverse agents powered by RL, LLMs, and beyond, the ability to explain agent policies in natural language is vital for reliable coexistence. We introduce a general-purpose framework that trains explanation-generating LLMs via reinforcement learning from…
Online policy learning directly in the physical world is a promising yet challenging direction for embodied intelligence. Unlike simulation, real-world systems cannot be arbitrarily accelerated, cheaply reset, or massively replicated, which makes scalable data collection, heterogeneous deployment, a…
This work investigates the resilience of contemporary large language models (LLMs) against frequent character-level perturbations. We examine three types of character-level perturbations including introducing numerous typos within words, shuffling the characters in each word, and inserting a large n…
As hubs of human activity, urban surfaces consist of a wealth of semantic entities. Segmenting these various entities from satellite imagery is crucial for a range of downstream applications. Current advanced segmentation models can reliably segment entities defined by physical attributes (e.g., bui…
Recent advancements in Vision Language Models (VLMs) have expanded their capabilities to interactive agent tasks, yet existing benchmarks remain limited to single-agent or text-only environments. In contrast, real-world scenarios often involve multiple agents interacting within rich visual and textu
Weakly supervised video anomaly detection (WS-VAD) involves identifying the temporal intervals that contain anomalous events in untrimmed videos, where only video-level annotations are provided as supervisory signals. However, a key limitation persists in WS-VAD, as dense frame-level annotations are
Precise and agile flight maneuvers are essential for quadrotor applications, yet traditional control methods are limited by their reliance on flat trajectories or computationally intensive optimization. Reinforcement learning (RL)-based policies offer a promising alternative by directly mapping obse…
Saliency is an important characteristic in 3D analysis, and saliency detection for 3D meshes has been extensively studied in visual computing. However, insufficient feature description poses a significant challenge for 3D mesh saliency maps, which consist with human visual perception that is indepen…
Vehicle trajectory prediction serves as a critical enabler for autonomous navigation and intelligent transportation systems. While existing approaches predominantly focus on temporal pattern extraction and vehicle-environment interaction modeling, they exhibit a fundamental limitation in addressing…
Large Generative Models (LGMs) such as GPT, Stable Diffusion, Sora, and Suno are trained on a huge amount of texts, images, videos, and audio that are extremely diverse from numerous domains. This large-scale training paradigm on diverse well-curated data enhances the creativity and diversity of the…
Spatial transcriptomics (ST) is an emerging technology that enables medical computer vision scientists to automatically interpret the molecular profiles underlying morphological features. Currently, however, most deep learning-based ST analyses are limited to two-dimensional (2D) sections, which can…
Traffic accidents present complex challenges for autonomous driving, often featuring unpredictable scenarios that hinder accurate system interpretation and responses. Nonetheless, prevailing methodologies fall short in elucidating the causes of accidents and proposing preventive measures due to the
The current large auto-regressive models can generate high-quality, high-resolution images, but these models require hundreds or even thousands of steps of next-token prediction during inference, resulting in substantial time consumption. In existing studies, Jacobi decoding, an iterative parallel d…
Personalized Federated Learning (PFL) is confronted with escalating security threats, yet existing defense strategies primarily concentrate on traditional federated learning, lacking robust defense mechanisms tailored for PFL. To fortify the robustness of PFL against stealthy malicious attacks, we p…
In this letter, the 3-degree of freedom (DOF) 3RPS-SPS parallel mechanism with active and passive branches is proposed to use a single active input to realize the expected position adjustment, which can reduce its manufacturing and maintenance costs. The principle of motion of the 3RPS-SPS parallel
The emergence of agentic recommender systems powered by Large Language Models (LLMs) represents a paradigm shift in personalized recommendations, leveraging LLMs’ advanced reasoning and role-playing capabilities to enable autonomous, adaptive decision-making. Unlike traditional recommendation approa…
Cross-domain talking head generation, such as animating a static cartoon animal photo with real human video, is crucial for personalized content creation. However, prior works typically rely on domain-specific frameworks and paired videos, limiting its utility and complicating its architecture with…
Quantized large language models (LLMs) have gained increasing attention and significance for enabling deployment in resource-constrained environments. However, emerging studies on a few calibration dataset-free quantization methods suggest that quantization may compromise the safety capabilities of…
This study introduces a multimodal large language model capable of not only accomplishing various heart sound tasks but also providing reasoning, marking an advancement in the field of medical diagnostics. The model’s innovation stems from a collaboration with experts to collect a novel dataset desi…
While chains-of-thought (CoT) have advanced complex reasoning in multimodal large language models (MLLMs), existing methods remain confined to text or static visual domains, often faltering in dynamic spatial reasoning tasks. To bridge this gap, we present GRASSLAND, a novel maze navigation benchmar
Instruction tuning in multimodal large language models (MLLMs) generally involves cooperative learning between a backbone LLM and a feature encoder of non-text input modalities. The major challenge is how to efficiently find the synergy between the two modules so that LLMs can adapt their reasoning
Multimodal RLHF usually happens after supervised finetuning (SFT) stage to continually improve vision-language models' (VLMs) comprehension. Conventional wisdom holds its superiority over continual SFT during this preference alignment stage. In this paper, we observe that the inherent value of multi…
Depth enhancement, which uses RGB images as guidance to convert raw signals from dToF into high-precision, dense depth maps, is a critical task in computer vision. Although existing super-resolution-based methods show promising results on public datasets, they often rely on idealized assumptions lik…
When performing reasoning tasks with user-specific requirements, such as strict output formats, large language models (LLMs) often prioritize reasoning over adherence to detailed instructions. Fine-tuning LLMs on supervised datasets to address this is impractical due to high computational costs and
Diffusion Transformer (DiT)-based generation models have achieved remarkable success in video generation. However, their inherent computational demands pose significant efficiency challenges. In this paper, we exploit the inherent temporal non-uniformity of real-world videos, and observe that videos…
The reliability of large language models remains a critical challenge, particularly due to their susceptibility to hallucinations and factual inaccuracies during text generation. Existing solutions either underutilize models’ self-correction with preemptive strategies or use costly post-hoc verifica
During robotic disaster relief missions, state estimation still faces significant challenges, especially when GNSS is denied or sensor perception undergoes degradation. In this paper, we introduce a degradation-aware LiDAR-Thermal-Inertial SLAM, DaLiTI, that leverages the complementary nature of mul
Despite the unprecedented success of applying Large Language Models (LLMs) to graph discriminative tasks such as node classification and link prediction, its potential for graph structure generation remains largely unexplored. To fill this crucial gap, this paper presents a systematic investigation…
Text-to-image generation models, especially Multimodal Diffusion Transformers (MMDiT), have shown remarkable progress in generating high-quality images. However, these models often face significant computational bottlenecks, particularly in attention mechanisms, which hinder their scalability and ef…
Autoregressive (AR) models have recently achieved state-of-the-art performance in text and image generation. However, their primary limitation is slow generation speed due to the token-by-token process. We ask an ambitious question: can a pre-trained AR model be adapted to generate outputs in just o…
Image Auto-regressive (AR) models have emerged as a powerful paradigm of visual generative models. Despite their promising performance, they suffer from slow generation speed due to the large number of sampling steps required. Although Distilled Decoding 1 (DD1) was recently proposed to enable few-s…
With the extensive deployment of Large Language Models (LLMs), ensuring their safety has become increasingly critical. However, existing defense methods often struggle with two key issues: (i) inadequate defense capabilities, particularly in domain-specific scenarios like chemistry, where a lack of…
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across multimodal tasks such as visual perception and reasoning, leading to good performance on various multimodal evaluation benchmarks. However, these benchmarks keep a static nature and overlap with the pre-training da…
Accurate and real-time stereo depth estimation is important for autonomous robots, such as autonomous aerial vehicles (AAVs). Due to the computation constraints of these miniaturized robots, current state-of-the-art algorithms deploy light-weight neural networks while using self-supervised online ad
In recent years, large language models (LLMs) have revolutionized the field of natural language processing. However, they often suffer from knowledge gaps and hallucinations. Graph retrieval-augmented generation (GraphRAG) enhances LLM reasoning by integrating structured knowledge from external grap
Contrastive learning is a prevalent technique in self-supervised vision representation learning, typically generating positive pairs by applying two data augmentations to the same image. Designing effective data augmentation strategies is crucial for the success of contrastive learning. Inspired by…
Large language models (LLMs) have demonstrated remarkable performance on various medical benchmarks, but their capabilities across different cognitive levels remain underexplored. Inspired by Bloom's Taxonomy, we propose a multi-cognitive-level evaluation framework for assessing LLMs in the medical…
We propose a novel automatic evaluation metric for open-ended text generation, which is a substantial improvement of the recently developed method, Fourier analysis of cross-entropy (FACE), hence, FACE-2. FACE-2 is a psycholinguistically inspired metric that extracts the dynamic patterns (spectrum)
Large language models (LLMs) are trained on extensive historical corpora, but their ability to understand time and maintain temporal awareness of time-evolving factual knowledge remains limited. Previous studies often neglect the critical aspect of utilizing knowledge from various sources. To addres…
Recent advancements in language models have led to significant improvements in mathematical reasoning across various benchmarks. However, most of these benchmarks rely on automatic evaluation methods that only compare final answers using heuristics, without verifying the underlying reasoning steps.
In this paper, we introduce FedMGP, a new paradigm for personalized federated prompt learning in vision-language models (VLMs). Existing federated prompt learning (FPL) methods often rely on a single, text-only prompt representation, which leads to client-specific overfitting and unstable aggregatio…
Parameter-efficient fine-tuning (PEFT) has revolutionized supervised fine-tuning, where LoRA and its variants gain the most popularity due to their low training costs and zero inference latency. However, LoRA tuning not only injects knowledgeable features but also noisy hallucination during fine-tun…
Ego-vision-based navigation in cluttered environments is crucial for mobile systems, particularly agile quadrotors. While learning-based methods have shown promise recently, head-to-head comparisons with cutting-edge optimization-based approaches are scarce, leaving open the question of where and to
Small land-air robots with rapid response and field operation capabilities hold significant potential for emergency rescue and field exploration applications. However, achieving stable and efficient mode transitions, along with effective terrain adaptability, remains a challenge. This letter present
The increasing demand to process long and high-resolution videos significantly burdens Large Vision-Language Models (LVLMs) due to the enormous number of visual tokens. Existing token reduction methods primarily prune tokens based on importance metrics, such as cumulative attention scores. However,…
Active Learning (AL) has been a powerful paradigm for improving model efficiency and performance by selecting the most informative data points for labeling and training. In recent active learning frameworks, Large Language Models (LLMs) have been employed not only for selection but also for generati…
Graphical User Interface (GUI) agents, powered by Large Foundation Models, have emerged as a transformative approach to automating human-computer interaction. These agents autonomously interact with digital systems via GUIs, emulating human actions such as clicking, typing, and navigating visual ele…
In tasks such as summarization and open-book question answering (QA), Large Language Models (LLMs) frequently experience “contextual hallucination”, where they generate irrelevant or incorrect responses despite having access to accurate information in the input. This issue often stems from the model…
Graphs in the real world are fragmented and dynamic, lacking collaboration akin to that observed in human societies. Existing paradigms present collaborative information collapse and forgetting, making collaborative relationships poorly autonomous and interactive information insufficient. Moreover,…
Utilizing robots for autonomous target search in complex and unknown environments can greatly improve the efficiency of search and rescue missions. However, existing methods have shown inadequate performance due to hardware platform limitations, inefficient viewpoint selection strategies, and conser
High-precision tiny object alignment remains a common and critical challenge for humanoid robots in real world. To address this problem, this paper proposes a vision-based framework for precisely estimating and controlling the relative position between a handheld tool and a target object for humanoi
With the increasing resolution of remote sensing imagery (RSI), large-size RSI has emerged as a vital data source for high-precision vector mapping of geographic objects. Existing methods are typically constrained to processing small image patches, which often leads to the loss of contextual informa…
Trajectory generation has garnered significant attention from researchers in the field of spatio-temporal analysis, as it can generate substantial synthesized human mobility trajectories that enhance user privacy and alleviate data scarcity. However, existing trajectory generation methods often focu…
Navigating in human-filled public spaces is a critical challenge for deploying autonomous robots in real-world environments. This paper introduces NaviDIFF, a novel Hamiltonian-constrained socially-aware navigation framework designed to address the complexities of human-robot interaction and sociall
Soft robots are inherently compliant and safe, making them suitable for human-interactive applications such as surgery. However, their nonlinear and hysteretic behavior, arising from the properties of soft materials, presents substantial challenges for accurate modeling and control. In this study, w
With the rapid advancement of Large Vision-Language Models (VLMs), concerns about their potential misuse and abuse have grown rapidly. Prior research has exposed VLMs’ vulnerability to jailbreak attacks, where carefully crafted inputs can lead the model to produce content that violates ethical and…
Large language models show impressive abilities in memorizing world knowledge, which leads to concerns regarding memorization of private information, toxic or sensitive knowledge, and copyrighted content. We introduce the problem of Large Scale Knowledge Washing, focusing on unlearning an extensive…
Weakly supervised video anomaly detection (WS-VAD) is tasked with pinpointing temporal intervals containing anomalous events within untrimmed videos, utilizing only video-level annotations. However, a significant challenge arises due to the absence of dense frame-level annotations, often leading to…
Large language model (LLM) agents have recently demonstrated impressive capabilities in various domains like open-ended conversation and multi-step decision-making. However, it remains challenging for these agents to solve strategic language games, such as Werewolf, which demand both strategic decis…
Reinforcement learning (RL) for continuous control often requires large amounts of online interaction data. Value-based RL methods can mitigate this burden by offering relatively high sample efficiency. Some studies further enhance sample efficiency by incorporating offline demonstration data to “…
Diffusion Models (DM) and Consistency Models (CM) are two types of popular generative models with good generation quality on various tasks. When training DM and CM, intermediate weight checkpoints are not fully utilized and only the last converged checkpoint is used. In this work, we find proper che…
Equipping large language models (LLMs) with latent-space memory has attracted increasing attention as they can extend the context window of existing language models. However, retaining information from the distant past remains a challenge. For example, MemoryLLM (Wang et al., 2024a), as a representa…
Vision-Language Models (VLMs) have already enabled a variety of real-world applications. The large parameter size of VLMs brings large memory and computation overhead which poses significant challenges for deployment. Post-Training Quantization (PTQ) is an effective technique to reduce the memory an…
Collaborative perception in unknown environments is crucial for multi-robot systems. With the emergence of foundation models, robots can now not only perceive geometric information but also achieve open-vocabulary scene understanding. However, existing map representations that support open-vocabular
In this paper, we tackle the problem of learning to play 3v3 multi-drone volleyball, a new embodied competitive task that requires both high-level strategic coordination and low-level agile control. The task is turn-based, multi-agent, and physically grounded, posing significant challenges due to it…
Recent MLLMs have demonstrated strong visual understanding and reasoning after large-scale multimodal pre-training. However, instruction-tuning is typically text-driven with limited visual supervision, leading to significant visual forgetting and degradation of pre-trained visual knowledge. Existing
This paper presents a novel hallucination detection method based on the internal states and output probabilities of large language models (LLMs) to address the common issue of hallucinations in model-generated content. We designed a new detection framework that extracts internal features such as hid…
Text-rich Graph Knowledge Bases (TG-KBs) have become increasingly crucial for answering queries by providing textual and structural knowledge. However, current retrieval methods often retrieve these two types of knowledge in isolation without considering their mutual reinforcement and existing hybri…
This paper tackles the challenging task of maintaining formation among multiple unmanned aerial vehicles (UAVs) while avoiding both static and dynamic obstacles during directed flight. The complexity of the task arises from its multi-objective nature, the large exploration space, and the sim-to-real
Accurate motion control in the face of disturbances within complex environments remains a major challenge in robotics. Classical model-based approaches often struggle with nonlinearities and unstructured disturbances, while reinforcement learning (RL)-based methods can be fragile when encountering u
Accurate 3D perception is essential for underwater vehicles in tasks such as seabed mapping, structural reconstruction, and environmental monitoring. However, optical cameras struggle in underwater environments due to light attenuation, scattering, and blurring, while forward-looking sonar suffers f
Multi-UAV pursuit-evasion, where pursuers aim to capture evaders, poses a key challenge for UAV swarm intelligence. Multi-agent reinforcement learning (MARL) has demonstrated potential in modeling cooperative behaviors, but most RL-based approaches remain constrained to simplifed simulations with li
For direct teleoperation tasks, the follower robot accomplishes tasks by strictly executing the inputs from the operator. However, the operator's physiological tremor seriously reduces the smoothness of the trajectory, especially in tasks relying on operator’s experience such as gluing, while the ra
In visual generation, the quadratic complexity of attention mechanisms results in high memory and computational costs, especially for longer token sequences required in high-resolution image or multi-frame video generation. To address this, prior research has explored techniques such as sparsificati…
Implicit neural representation (INR) has now been thrust into the limelight with its flexibility in high-fidelity flow field reconstruction tasks. However, the lack of standard benchmarking datasets and the grid independence assumption for INR-based methods hinder progress and adoption in real-world…
Voxel-based 3D object detectors have achieved remarkable performance in point cloud perception, yet their high computational and memory demands pose significant challenges for deployment on resource-constrained edge devices. Post-training quantization (PTQ) provides a practical means to compress mod…
Multi-species animal pose estimation has emerged as a challenging yet critical task, hindered by substantial visual diversity and uncertainty. This paper challenges the problem by efficient prompt learning for Vision-Language Pretrained (VLP) models, e.g. CLIP, aiming to resolve the cross-species ge…
Diffusion transformers (DiT) have demonstrated exceptional performance in video generation. However, their large number of parameters and high computational complexity limit their deployment on edge devices. Quantization can reduce storage requirements and accelerate inference by lowering the bit-wi…
In typical multimodal tasks, such as Visual Question Answering (VQA), adversarial attacks targeting a specific image and question can lead large vision-language models (LVLMs) to provide incorrect answers. However, it is common for a single image to be associated with multiple questions, and LVLMs m…
Large Language Models (LLMs) achieve impressive reasoning capabilities at the cost of substantial inference overhead, posing substantial deployment challenges. Although distilled Small Language Models (SLMs) significantly enhance efficiency, their performance suffers as they fail to follow LLMs' rea…
The integration of external knowledge through Retrieval-Augmented Generation (RAG) has become foundational in enhancing large language models (LLMs) for knowledge-intensive tasks. However, existing RAG paradigms often overlook the cognitive step of applying knowledge, leaving a gap between retrieved
Visual place recognition is a critical component of robust simultaneous localization and mapping systems. Conventional approaches primarily rely on RGB imagery, but their performance degrades significantly in extreme environments, such as those with poor illumination and airborne particulate interfe
The Chain-of-Thought (CoT) paradigm has become a pivotal method for solving complex problems with large language models (LLMs). However, its application to domain-specific tasks remains challenging, as LLMs often fail to decompose tasks accurately or execute subtasks effectively. This paper introduc…
LiDARs are widely used in autonomous robots due to their ability to provide accurate environment structural information. However, the large size of point clouds poses challenges in terms of data storage and transmission. In this paper, we propose a novel point cloud compression and transmission fram
Class incremental learning (CIL) aims to enable models to continuously learn new classes without catastrophically forgetting old ones. A promising direction is to learn and use prototypes of classes during incremental updates. Despite simplicity and intuition, we find that such methods suffer from i…
Large Language Models (LLMs) have shown promising potential in the medical domain, assisting with tasks like clinical note generation and patient communication. However, current LLMs are limited to text-based communication, hindering their ability to interact with diverse forms of information in cli…
We propose ReinFlow, a simple yet effective online reinforcement learning (RL) framework that fine-tunes a family of flow matching policies for continuous robotic control. Derived from rigorous RL theory, ReinFlow injects learnable noise into a flow policy’s deterministic path, converting the flow i…
Deep neural networks have achieved remarkable performance across a variety of applications. However, their decision-making processes are opaque. In contrast, k-nearest neighbor (k-NN) provides interpretable predictions by relying on similar cases, but it lacks important capabilities of neural networ
Lightweight direct Time-of-Flight (dToF) sensors are ideal for 3D sensing on mobile devices. However, due to the manufacturing constraints of compact devices and the inherent physical principles of imaging, dToF depth maps are sparse and noisy. In this paper, we propose a novel video depth completio…
Graph Neural Networks (GNNs) are known to be prone to adversarial attacks, among which backdoor attack is a major security threat. By injecting backdoor triggers into a graph and assigning a target class label to nodes attached to the triggers, the attacker can mislead the GNN model trained on the p
Sparse linear solvers are fundamental to science and engineering, applied in partial differential equations (PDEs), scientific computing, computer vision, and beyond. Indirect solvers possess characteristics that make them undesirable as stable differentiable modules; existing direct solvers, though…
Despite significant advancements in large language models (LLMs), the rapid and frequent integration of small-scale experiences, such as interactions with sur- rounding objects, remains a substantial challenge. Two critical factors in assimilating these experiences are (1) **Efficacy**: the ability…
Traditional machine societies rely on data-driven learning, overlooking interactions and limiting knowledge acquisition from model interplay. To address these issues, we revisit the development of machine societies by drawing inspiration from the evolutionary processes of human societies. Motivated…
Vision-Language-Action (VLA) models have made substantial progress by leveraging the robust capabilities of Visual Language Models (VLMs). However, VLMs’ significant parameter size and autoregressive (AR) decoding nature impose considerable computational demands on VLA models. While Speculative Deco
As a new paradigm of visual content generation, autoregressive text-to-image models suffer from slow inference due to their sequential token-by-token decoding process, often requiring thousands of model forward passes to generate a single image. To address this inefficiency, we propose Speculative J…
Diffusion models have recently emerged as powerful neural solvers for combinatorial optimization (CO). However, existing approaches fail to reveal how variables are progressively determined during inference, making the final solution opaque until the last step. To address this limitation, we propose…
The choice of a suitable visual language projector (VLP) is critical to the successful training of large visual language models (LVLMs). Mainstream VLPs can be broadly categorized into compressed and uncompressed projectors, and each offers distinct advantages in performance and computational effici
Large Multimodal Models (LMMs) face limitations in geometric reasoning due to insufficient Chain of Thought (CoT) image-text training data. While existing approaches leverage template-based or LLM-assisted methods for geometric CoT data creation, they often face challenges in achieving both diversit
Large language models hold promise for addressing medical challenges, such as medical diagnosis reasoning, research knowledge acquisition, clinical decision-making, and consumer health inquiry support. However, they often generate hallucinations due to limited medical knowledge. Incorporating extern…
Recently, Knowledge Graphs (KGs) have been successfully coupled with Large Language Models (LLMs) to mitigate their hallucinations and enhance their reasoning capability, e.g., KG-based retrieval-augmented framework. However, current KG-LLM frameworks lack rigorous uncertainty estimation, limiting t…
Diffusion transformers have demonstrated remarkable performance in visual generation tasks, such as generating realistic images or videos based on textual instructions. However, larger model sizes and multi-frame processing for video generation lead to increased computational and memory costs, posin…
Speech large language models (LLMs) have emerged as a prominent research focus in speech processing. In this work, we introduce VocalNet, a series of high-performance speech LLMs featuring a scalable and model-agnostic training framework as well as a novel multi-token prediction (MTP) paradigm for s
Robot sports, characterized by well-defined objectives, explicit rules, and dynamic interactions, present ideal scenarios for demonstrating embodied intelligence. In this paper, we present VolleyBots, a novel robot sports testbed where multiple drones cooperate and compete in the sport of volleybal…
Large Vision-Language Action (VLA) models have shown significant potential for embodied AI. However, their predominant training via supervised fine-tuning (SFT) limits generalization due to susceptibility to compounding errors under distribution shifts. Reinforcement learning (RL) offers a path to…
Precise and agile flight maneuvers are essential for quadrotor applications, yet traditional control methods are limited by their reliance on flat trajectories or computationally intensive optimization. Reinforcement learning (RL)-based policies offer a promising alternative by directly mapping obse
In this letter, a tendon-driven continuum robotic manipulator with three individual continuum sections is developed and manufactured. The main contribution is that we propose a robust and accurate shape estimation method based on the fusion of multi-IMUs for the manipulator, under the PCC (Piecewise
Graph Neural Networks (GNNs) have shown great promise in learning node embeddings for link prediction (LP). While numerous studies improve the overall GNNs' LP performance, none have explored their varying performance across different nodes and the underlying reasons. To this end, we demystify which…
Recent years have witnessed the rapid progress and broad application of diffusion probabilistic models (DPMs). Sampling from DPMs can be viewed as solving an ordinary differential equation (ODE). Despite the promising performance, the generation of DPMs usually consumes much time due to the large nu…
Learning Nash equilibrium (NE) in complex zero-sum games with multi-agent reinforcement learning (MARL) can be extremely computationally expensive. Curriculum learning is an effective way to accelerate learning, but an under-explored dimension for generating a curriculum is the difficulty-to-learn o…
This letter investigates the multi-agent cooperative exploration problem, which requires multiple agents to explore an unseen environment via sensory signals in a limited time. A popular approach to exploration tasks is to combine active mapping with planning. Metric maps capture the details of the
Structure-based drug design (SBDD) aims to generate 3D ligand molecules that bind to specific protein targets. Existing 3D deep generative models including diffusion models have shown great promise for SBDD. However, it is complex to capture the essential protein-ligand interactions exactly in 3D sp…
The Video-Grounded Dialogue generation (VDG) is a challenging task requiring a comprehensive understanding of the multi-modal information to produce a pertinent response. However, VDG models may rely on dataset bias as a shortcut and fail to learn the multi-modal knowledge from both video and audio.…
In text-conditioned image retrieval (TCIR), the combination of a reference image and modification text forms a query tuple, aiming to locate the most congruent target image within a dataset. The advantages of rich image semantic information and text flexibility are combined in this manner for more a…
Teaching to improve student models (e.g., knowledge distillation) is an extensively studied methodology in LLMs. However, in human education, teaching enhances not only the students but also the teachers by fostering more rigorous and clearer reasoning, as well as deeper knowledge building. We ask:…
Target tracking is a fundamental task in the domain of robotics. The effectiveness of target tracking hinges upon various factors, such as tracking distance, occlusions, collision avoidance, etc. However, few existing works can simultaneously tackle these considerations of tracking single and multip…
"This paper studies the challenging cross-domain few-shot object detection (CD-FSOD), aiming to develop an accurate object detector for novel domains with minimal labeled examples. While transformer-based open-set detectors, such as DE-ViT, show promise in traditional few-shot object detection, thei…
Understanding and accurately explaining compatibility relationships between fashion items is a challenging problem in the burgeoning domain of AI-driven outfit recommendations. Present models, while making strides in this area, still occasionally fall short, offering explanations that can be element…
Human and model-generated texts can be distinguished by examining the magnitude of likelihood in language. However, it is becoming increasingly difficult as language model’s capabilities of generating human-like texts keep evolving. This study provides a new perspective by using the relative likelih…
Diffusion models have achieved remarkable progress in the field of image generation due to their outstanding capabilities. However, these models require substantial computing resources because of the multi-step denoising process during inference. While traditional pruning methods have been employed…
Diffusion Transformers (DiT) excel at image and video generation but face computational challenges due to the quadratic complexity of self-attention operators. We propose DiTFastAttn, a post-training compression method to alleviate the computational bottleneck of DiT. We identify three key redundanc…
Structured data offers an efficient means of organizing information. Exsisting text-serialization based methods for processing structured data using large language models (LLMs) are not designed to explicitly capture the heterogeneity of structured data. Such methods are suboptimal for LLMs to proce…
Continual learning (CL) has shown promising results and comparable performance to learning at once in a fully supervised manner. However, CL strategies typically require a large number of labeled samples, making their real-life deployment challenging. In this work, we focus on semi-supervised contin…
In the rapidly growing digital economy, protecting intellectual property (IP) associated with digital products has become increasingly important. Within this context, machine learning (ML) models, being highly valuable digital assets, have gained significant attention for IP protection. This paper…
To improve the precision of the 2RPU/UPR+R+P hybrid robot and fulfill production requirements, error compensation was explored. The robot's fixed coordinate system was first used to analyze the workbench error mapping matrix. Next, the correlation between the joint geometric errors and the moving pl
Post-training quantization (PTQ) has emerged as a promising technique to reduce the cost of large language models (LLMs). Specifically, PTQ can effectively mitigate memory consumption and reduce computational overhead in LLMs. To meet the requirements of both high efficiency and performance across d…
Attributed graph clustering is an unsupervised task that partitions nodes into different groups. Self-supervised learning (SSL) shows great potential in handling this task, and some recent studies simultaneously learn multiple SSL tasks to further boost performance. Currently, different SSL tasks ar…
Open set recognition (OSR) requires the model to classify samples that belong to closed sets while rejecting unknown samples during test. Currently, generative models often perform better than discriminative models in OSR, but recent studies show that generative models may be computationally infeasi…
In recent years there has been significant progress in the development of text-to-image generative models. Evaluating the quality of the generative models is one essential step in the development process. Unfortunately the evaluation process could consume a significant amount of computational resour…
Recent research has underscored the efficacy of Graph Neural Networks (GNNs) in modeling diverse geometric structures within graph data. However, real-world graphs typically exhibit geometrically heterogeneous characteristics, rendering the confinement to a single geometric paradigm insufficient for…
3D Semantic Scene Completion (SSC) has emerged as a novel task in vision-based holistic 3D scene understanding. Its objective is to densely predict the occupancy and category of each voxel in a 3D scene based on input from either LiDAR or images. Currently, many transformer-based semantic scene comp…
Heart sound auscultation holds significant importance in the diagnosis of congenital heart disease. However, existing methods for Heart Sound Diagnosis (HSD) tasks are predominantly limited to a few fixed categories, framing the HSD task as a rigid classification problem that does not fully align wi…
We introduce a novel semi-supervised learning approach, named Teacher-Student Bayesian Optimization ($\texttt{TSBO}$), integrating the teacher-student paradigm into BO to minimize expensive labeled data queries for the first time. $\texttt{TSBO}$ incorporates a teacher model, an unlabeled data sampl…
According to the Entropy Rate Constancy (ERC) principle, the information density of a text is approximately constant over its length. Whether this principle also applies to nonverbal communication signals is still under investigation. We perform empirical analyses of video-recorded dialogue data and…
Recently, cross-source point cloud registration from different sensors has become a significant research focus. Although current methods have advanced homogenous point cloud registration, challenges persist in the cross-source domain due to varying point cloud densities from different sensors and mi
Huge progress has been made in LiDAR 3D semantic segmentation, but there are two under-explored imbalances on the radial axis: points are unevenly concentrated on the near side, and the distribution of foreground object instances is skewed to the near side. This leads the training of the model to fa…
Generating ligand molecules that bind to specific protein targets via generative models holds substantial promise for advancing structure-based drug design. Existing methods generate molecules from scratch without reference or template ligands, which poses challenges in model optimization and may yi…
DETR is a novel end-to-end transformer architecture object detector which significantly outperforms classic detectors when scaling up. In this paper we focus on the compression of DETR with knowledge distillation. While knowledge distillation has been well-studied in classic detectors there is a lac…
The `pre-train, prompt, predict' paradigm of large language models (LLMs) has achieved remarkable success in open-domain question answering (OD-QA). However, few works explore this paradigm in multi-document question answering (MD-QA), a task demanding a thorough understanding of the logical associa…
"Existing methods enhance open-vocabulary object detection by leveraging the robust open-vocabulary recognition capabilities of Vision-Language Models (VLMs), such as CLIP. However, two main challenges emerge: (1) A deficiency in concept representation, where the category names in CLIP’s text space…
Agents built with large language models (LLMs) have shown great potential across a wide range of domains. However, in complex decision-making tasks, pure LLM-based agents tend to exhibit intrinsic bias in their choice of actions, which is inherited from the model's training data and results in subop…
Online dating platforms have gained widespread popularity as a means for individuals to seek potential romantic relationships. While recommender systems have been designed to improve the user experience in dating platforms by providing personalized recommendations, increasing concerns about fairness…
There is a recent need in the LiDAR perception field for unifying multiple tasks in a single strong network with improved performance, as opposed to using separate networks for each task. In this paper, we introduce a new LiDAR multi-task learning paradigm based on the transformer. The proposed LiDA…
Publishing open-source academic video recordings is an emergent and prevalent approach to sharing knowledge online. Such videos carry rich multimodal information including speech, the facial and body movements of the speakers, as well as the texts and pictures in the slides and possibly even the pap…
Existing Large Language Models (LLMs) usually remain static after deployment, which might make it hard to inject new knowledge into the model. We aim to build models containing a considerable portion of self-updatable parameters, enabling the model to integrate new knowledge effectively and efficien…
Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in visual perception and understanding. However, these models also suffer from hallucinations, which limit their reliability as AI systems. We believe that these hallucinations are partially du…
Generating dialogue grounded in videos requires a high level of understanding and reasoning about the visual scenes in the videos. However, existing large visual-language models are not effective due to their latent features and decoder-only structure, especially with respect to spatio-temporal rela…
Large language models (LLMs) have shown substantial progress in natural language understanding and generation, proving valuable especially in the medical field. Despite advancements, challenges persist due to the complexity and diversity inherent in medical tasks, which can be categorized as knowled…
"Few-step diffusion models, which enable high-quality text-to-image generation with only a few denoising steps, have substantially reduced inference time. However, considerable memory consumption (5-10GB) still poses limitations for practical deployment on mobile devices. Post-Training Quantization…
In this work, we introduce <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">OmniDrones</i> , an efficient and flexible platform tailored for reinforcement learning in drone control, built on Nvidia's Omniverse Isaac Sim. It employs a bottom-up design
Domain adaptation has become an attractive learning paradigm, as it can leverage source domains with rich labels to deal with classification tasks in an unlabeled target domain. A few recent studies develop domain adaptation approaches for graph-structured data. In the case of node classification ta…
"We study a challenging task: text-to-motion synthesis, aiming to generate motions that align with textual descriptions and exhibit coordinated movements. Currently, the part-based methods introduce part partition into the motion synthesis process to achieve finer-grained generation. However, these…
Semi-supervised continual learning (SSCL) has attracted significant attention for addressing catastrophic forgetting in semi-supervised data. Knowledge distillation, which leverages data representation and pair-wise similarity, has shown significant potential in preserving information in SSCL. Howev…