442 accepted papers
This document presents the outcomes of the Dagstuhl Seminar "Roadmap for Responsible Robotics," held in September 2023 at the Leibniz Centre for Informatics, Schloss Dagstuhl, Germany. The seminar brought together researchers from Robotics, Computer Science, Social and Cognitive Sciences, and Philos…
Training-free 3D editing aims to modify 3D shapes based on human instructions without model finetuning. It plays a crucial role in 3D content creation. However, existing approaches often struggle to produce strong or geometrically stable edits, largely due to inconsistent latent anchors introduced b
Large-scale video diffusion models exhibit strong world-simulation and temporal reasoning capabilities, yet their potential as zero-shot image editors remains underexplored. We present \ifedit IF-Edit (Image Edit by Generating Frames), a tuning-free framework that repurposes pre-trained image-to-vid
Existing theoretical work on Bayes-optimal fair classifiers usually considers a single (binary) sensitive feature. In practice, individuals are often defined by multiple sensitive features. In this paper, we characterize the Bayes-optimal fair classifier for multiple sensitive features under general
Predicting transcriptional responses to genetic perturbations is a central problem in functional genomics. In practice, perturbation responses are rarely gene-independent but instead manifest as coordinated, program-level transcriptional changes among functionally related genes. However, most existi…
Conditional image generation augments text-to-image synthesis with structural, spatial, or stylistic priors and is used in many domains. However, current methods struggle to harmonize guidance from both sources when conflicts arise: 1) input-level conflict, where the semantics of the conditioning im…
Retrieving molecular structures from tandem mass spectra is a crucial step in rapid compound identification. Existing retrieval methods, such as traditional mass spectral library matching, suffer from limited spectral library coverage, while recent cross-modal representation learning frameworks ofte
Multimodal large language models (MLLMs) have shown considerable potential in chart understanding and reasoning tasks. However, they still struggle with high information density (HID) charts characterized by multiple subplots, legends, and dense annotations due to three major challenges: (1) limited
Despite recent advances, multimodal large language models continue to struggle with visual mathematical problem solving. Some recent works recognize that visual perception is a bottleneck in visual mathematical reasoning, but their solutions are limited to improving the extraction and interpretation…
Multi-instance image generation (MIG) remains a significant challenge for modern diffusion models due to key limitations in achieving precise control over object layout and preserving the identity of multiple distinct subjects. To address these limitations, we introduce **ContextGen**, a novel Diffu…
Object-Goal Navigation (ObjectNav) requires an embodied agent to search for and reach a target object category in previously unseen environments using only onboard egocentric observations, which is a fundamental capability for long-horizon autonomous robots. Current Object-Goal Navigation methods ty…
Dual-lens video inpainting aims to simultaneously restore missing or corrupted contents in videos captured by each lens of binocular systems. Although preliminary explorations have been conducted, existing methods still face two key challenges: limited exploitation of long-range reference informatio
Dynamic indoor environments pose significant challenges for autonomous robots, as objects frequently move and scenes continuously change, requiring robust scene representation and adaptive navigation strategies. In this work, we introduce DSSM-SG, a dynamic open-vocabulary 3D scene graph framework e…
With the rapid deployment of multimodal large language models (MLLMs), disputes regarding model ownership have become increasingly frequent, raising significant concerns about intellectual property protection. In this paper, we propose a framework for generating copyright triggers for MLLMs, enablin
The quadratic complexity of standard attention mechanisms poses a significant scalability bottleneck for large language models (LLMs) in long-context scenarios. While hybrid attention strategies that combine sparse and full attention within a single model offer a viable solution, they typically empl…
In this paper, we explore how to empower general-purpose Vision-Language Models (VLMs) to control humanoid agents. General-purpose VLMs (e.g., GPT-4) exhibit strong open-world generalization, and remove the need for additional fine-tuning data. To build such an agent, two key components are required…
High-quality 3D scene representation in radiance fields relies on accurate camera poses which are often difficult to acquire in real-world scenarios. An effective solution is to use RGB images for the joint optimization of radiance fields and camera poses, an approach that has been well explored in
Research on the intelligent interpretation of all-weather, all-time Synthetic Aperture Radar (SAR) is crucial for advancing remote sensing applications. In recent years, although Visual Language Models (VLMs) have demonstrated strong open-world understanding capabilities on RGB images, their perform
Simulation-Based Inference (SBI) is critical for scientific discovery, with generative models offering a promising path toward efficient inference. However, existing methods struggle with effective multimodal modeling. They often rely on brute-force fusion strategies that ignore the structural dispa…
3D Gaussian Splatting has revolutionized neural rendering with real-time performance. However, scaling this approach to large scenes using Level-of-Detail methods faces critical challenges: inefficient serial traversal consuming over 60% of rendering time, and redundant Gaussian-tile pairs that incu
Recent Video-to-Audio (V2A) methods have achieved remarkable progress, enabling the synthesis of realistic, high-quality audio. However, they struggle with fine-grained temporal control in multi-event scenarios or when visual cues are insufficient, such as small regions, off-screen sounds, or occlud
We present \textbf{Frequency-Aware Dynamic Gaussian Splatting (FAGS)}, a novel approach to mitigating motion blur in 4D reconstruction, particularly under novel viewpoints. This blur stems from a fundamental spectral conflict in existing methods, which struggle to \textbf{balance high-frequency ren…
Multimodal image fusion (MMIF) aims to integrate complementary information from different modalities into a single fused image that preserves *fine local details* while maintaining *globally consistent appearance*. Most existing approaches build shared representations on 2D feature grids, which exce…
Domain-specific embedding models have shown promise for applications that require specialized semantic understanding, such as coding agents and financial retrieval systems, often achieving higher performance gains than general models. However, state-of-the-art embedding models are typically based on…
The inherent semantic ambiguity of "many-to-many", where one video matches multiple texts and vice versa, aggravates the difficulty in text-video retrieval. The dominant deterministic embeddings only struggle to capture the mean semantics, while existing probabilistic methods fail to distinguish har
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language understanding, yet processing long visual token sequences remains computationally expensive. Existing approaches mitigate this cost by reducing image tokens, either by discarding them after the visual encod
LiDAR point cloud is essential for autonomous vehicles, but motion distortions from dynamic objects degrade the data quality. While previous work has considered distortions caused by ego motion, distortions caused by other moving objects remain largely overlooked, leading to errors in object shape a
This work presents Insert Anything, a unified framework for reference-based image insertion that seamlessly integrates objects from reference images into target scenes under flexible, user-specified control guidance. Instead of training separate models for individual tasks, our approach is trained o
Video data provides a rich source beyond expensive action-labeled data for advancing robot learning. Recent approaches have demonstrated promising potential in leveraging video data by learning latent actions for policy training. The latent action tokenizer encodes latent actions between successive
Generating coherent and communicative visual sequences, such as image sequences and videos, remains a significant challenge for current multimodal systems. Despite advances in visual quality and the integration of world knowledge, existing models still struggle to maintain logical flow, often result…
Autoregressive large language models (LLMs) have unified a vast range of language tasks, inspiring preliminary efforts in autoregressive (AR) video generation. Existing AR video generators either diverge from standard LLM architectures, depend on bulky external text encoders, or incur prohibitive la…
Object-level SLAM offers structured and semantically meaningful environment representations, making it more interpretable and suitable for high-level robotic tasks. However, most existing approaches rely on RGB-D sensors or monocular views, which suffer from narrow fields of view, occlusion sensitiv
Recent advances in Vision-Language-Action (VLA) models demonstrate that visual signals can effectively complement sparse action supervisions. However, letting VLA directly predict high-dimensional visual states can distribute model capacity and incur prohibitive training cost, while compressing visu
Tracking-any-point (TAP) answers query-conditioned correspondence but leaves the dense, all-pairs structure of a video implicit. We formulate All-Pairs Tracking (APT): given a video, predict dense displacement and visibility for every source-target frame pair, from which per-pixel trajectories can b
Text-to-music generation technology is progressing rapidly, creating new opportunities for musical composition and editing. However, existing music editing methods often fail to preserve the source music
Reconstructing visual stimuli from fMRI signals is a central challenge bridging machine learning and neuroscience. Recent diffusion-based methods typically map fMRI activity to a single neural embedding, using it as static guidance throughout the entire generation process. However, this fixed guidan…
High-precision controllable remote sensing image generation is both meaningful and challenging. Existing diffusion models often produce low-fidelity objects due to their inability to adequately capture morphological details, which may affect the robustness and reliability of object detection models.…
Robotic systems demand accurate and comprehensive 3D environment perception, requiring simultaneous capture of photo-realistic appearance (optical), precise layout shape (geometric), and open-vocabulary scene understanding (semantic). Existing methods typically achieve only partial fulfillment of th…
Video Temporal Grounding (VTG), the task of localizing video segments from text queries, struggles in open-world settings due to limited dataset scale and semantic diversity, causing performance gaps between common and rare concepts. To overcome these limitations, we introduce OmniVTG, a new large-s
This work enables everyday devices, e.g., smartphones, to dynamically capture open-ended 3D scenes with rich, expandable semantics for immersive virtual worlds. While 3DGS and foundation models hold promise for semantic scene understanding, existing solutions suffer from unscalable semantic integrat…
3D reconstruction of transparent objects from multiple views has been a long-standing challenge. In contrast to opaque objects, transparent objects exhibit complex refraction that causes serious image distortions, resulting in a highly ill-posed problem. Existing reconstruction methods commonly depe
We explore the oscillatory behavior observed in inversion methods applied to large-scale flow models, including text-to-image and text-to-video. By employing an augmented fixed-point-inspired iterative approach to invert real-world images, we observe that the solution does not achieve convergence, i
Planar structures, ubiquitous in man-made indoor environments, enable compact and accurate scene abstraction for various downstream tasks. Recent methods distill planar features into learning-based MVS geometries to obtain coherent 3D plane estimation from multi-view inputs. However, the lack of exp…
This paper explores parallel thinking for Multi-modal Large Language Models (MLLMs), aiming to improve Chain-of-Thought (CoT) through multiple diverse reasoning paths. We guide the model to list multiple visual key points and develop an independent reasoning path for each. Therefore, we term this me
The advancement of diffusion-based text-to-music generation has opened new avenues for zero-shot music editing. However, existing methods fail to achieve context-aware editing, which requires altering specific stems while strictly preserving the background accompaniment. This limitation severely hin…
We present \textsc{GenRep}, a unified image understanding and synthesis model that jointly conducts discriminative learning and generative modeling in one training session. By leveraging Monte Carlo approximation, \textsc{GenRep} distills distributional knowledge embedded in diffusion models to gu…
We present Recurrent Video Masked-Autoencoders (RVM): a novel approach to video representation learning that leverages recurrent computation to model the temporal structure of video data. RVM couples an asymmetric masking objective with a transformer-based recurrent neural network to aggregate infor
Reconstructing dynamic scenes with multiple interacting humans and objects from sparse-view inputs is a critical yet challenging task, essential for creating high-fidelity digital twins for robotics and VR/AR. This problem, which we term Multi-Human Multi-Object (MHMO) rendering, presents two signif…
Zero-shot object navigation in unknown environments presents significant challenges, mainly due to two key limitations: insufficient semantic guidance leads to inefficient exploration, while limited spatial memory resulting from environmental structure causes entrapment in local regions. To address …
Rigged 3D assets are fundamental to 3D deformation and animation. However, existing 3D generation methods face challenges in generating animatable geometry, while rigging techniques lack fine-grained structural control over skeleton creation. To address these limitations, we introduce Stroke3D, a no…
Recent Large Language Models (LLMs) have made remarkable progress, but they still struggle with complex reasoning tasks such as logical deduction and planning. This is partly because they rely primarily on token-level probability relationships, which limits their ability to reason effectively. In t…
Multi-modal Large Language Models (MLLMs) have achieved remarkable progress in video temporal grounding (VTG) with the introduction of reinforcement learning (RL) for generating reasoning paths. However, existing models often produce superficial reasoning, such as providing generic video description…
Human motions are compositional: complex behaviors can be described as combinations of simpler primitives. However, existing approaches primarily focus on forward modeling, e.g., learning holistic mappings from text to motion or composing a complex motion from a set of motion concepts. In this paper
Monocular normal estimation for transparent objects is critical for laboratory automation, yet it remains challenging due to complex light refraction and reflection. These optical properties often lead to catastrophic failures in conventional depth and normal sensors, hindering the deployment of emb…
Underwater 3D reconstruction remains challenging due to the intricate interplay between light scattering and environment dynamics. While existing methods yield plausible reconstruction with rigid scene assumptions, they struggle to capture temporal dynamics and remain sensitive to observation noise.…
Vision-Language Navigation (VLN) requires an agent to navigate 3D environments following natural language instructions. During navigation, existing agents commonly encounter perceptual uncertainty, such as insufficient evidence for reliable grounding or ambiguity in interpreting spatial cues, yet th…
Parallel test-time scaling typically trains separate generation and verification models, incurring high training and inference costs. We propose Advantage Decoupled Preference Optimization (ADPO), a unified reinforcement learning framework that jointly learns answer generation and self-verification
Speculative decoding (SD) addresses the high inference costs of large language models (LLMs) by having lightweight drafters generate candidates for large verifiers to validate in parallel. Existing draft-verify methods use binary decisions: accept or fully recompute. Yet we find that many rejected t…
Scalable robot learning is hindered by the high cost of acquiring diverse, high-quality embodied data. Existing data generation approaches partially mitigate this issue but typically depend on hard-to-access hardware and labor-intensive manual effort, with limited generalization to diverse scene con
Inverse design aims to design the input variables of a physical system to optimize a specified objective function, typically formulated as a search or optimization problem. However, in 3D domains, the design space grows exponentially, rendering exhaustive grid-based searches infeasible. Recent advan…
The increasing demand for controllable outputs in text-to-image generation has spurred advancements in multi-instance generation (MIG), allowing users to define both instance layouts and attributes. However, unlike image-conditional generation methods such as ControlNet, MIG techniques have not been…
Quantizing large language models (LLMs) to 1-bit precision significantly reduces computational costs, but existing quantization techniques suffer from noticeable performance degradation when using weight and activation precisions below 4 bits (W4A4). In this paper, we propose a post-training quantiz…
Text embedding models play a cornerstone role in AI applications, such as retrieval-augmented generation (RAG). While general-purpose text embedding models demonstrate strong performance on generic retrieval benchmarks, their effectiveness diminishes when applied to private datasets (e.g., company-s…
Diffusion-based Text-to-Image (T2I) models have demonstrated significant potential in image restoration. However, existing models continue to grapple with challenges such as complex training and prompt design. We introduce a new perspective for improving image restoration by injecting knowledge from…
Machine unlearning is a critical area of research aimed at safeguarding data privacy by enabling the removal of sensitive information from machine learning models. One unique challenge in this field is catastrophic unlearning, where erasing specific data from a well-trained model unintentionally rem…
In recent years, 3D Gaussian Splatting (3D-GS)based scene representation demonstrates significant potential in real-time rendering and training efficiency. However, most existing methods primarily focus on single-map reconstruction, while the registration and fusion of multiple 3D-GS submaps remain
Human motion generative models have enabled promising applications, but the ability of text-to-motion (T2M) models to produce realistic motions raises security concerns if exploited maliciously. Despite growing interest in T2M, limited research focus on safeguarding these models against adversarial…
Video inpainting aims to fill in corrupted regions of the video with plausible contents. Existing methods generally assume that the locations of corrupted regions are known, focusing primarily on the "how to inpaint". This reliance necessitates manual annotation of the corrupted regions using binary…
Physical intelligence for aerial robots greatly enhances grasping and perching performance, but remains in emerging stages. This letter proposes a novel bistable soft gripper for aerial robots with high response speed (0.11s), large holding force (23.47N), and active/passive adaptive grasping and pe
Reconstructing perceived images from human brain activity forms a crucial link between human and machine learning through Brain-Computer Interfaces. Early methods primarily focused on training separate models for each individual to account for individual variability in brain activity, overlooking va…
While deep neural networks have made remarkable progress in various tasks, their performance typically deteriorates and faces insecurity when tested in out-of-distribution (OOD) scenarios. Many OOD methods focus on extracting domain-invariant features but neglect whether these features are unique to…
Recent advances in Emotional Support Conversation (ESC) have improved emotional support generation by fine-tuning Large Language Models (LLMs) via Supervised Fine-Tuning (SFT). However, common psychological errors still persist. While Direct Preference Optimization (DPO) shows promise in reducing su
The limited availability of high-quality training data poses a major obstacle in data-driven PDE solving, where expensive data collection and resolution constraints severely impact the ability of neural operator networks to learn and generalize the underlying physical system. To address this challen…
Top-leading solutions for Video Scene Graph Generation (VSGG) typically adopt an offline pipeline.Though demonstrating promising performance, they remain unable to handle real-time video streams and consume large GPU memory. Moreover, these approaches fall short in temporal reasoning, merely aggreg…
Video inpainting aims to fill the missing regions in video with spatial-temporally coherent contents. Existing methods usually treat the missing contents as a whole and adopt a hybrid objective containing a reconstruction loss and an adversarial loss to train the model. However, these two kinds of l
Text-to-3D generation automates 3D content creation from textual descriptions, which offers transformative potential across various fields. However, existing methods often struggle to align generated content with human preferences, limiting their applicability and flexibility. To address these limit…
Image-conditioned generation methods, such as depth- and canny-conditioned approaches, have demonstrated remarkable abilities for precise image synthesis. However, existing models still struggle to accurately control the content of multiple instances (or regions). Even state-of-the-art models like F…
Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild env…
Sparse Mixture-of-Experts (SMoE) architectures are widely used in large language models (LLMs) due to their computational efficiency. However, though only a few experts are activated for each token, SMoE still requires loading all expert parameters, leading to high memory usage and challenges in dep
Language-based human motion understanding focuses on describing human motions using natural language descriptions. Conversely, human motion generation aims to generate human motions from textual inputs. Despite significant progress in both fields, further advancements are hindered by two primary cha…
Instruction-based image editing enables precise modifications via natural language prompts, but existing methods face a precision-efficiency tradeoff: fine-tuning demands massive datasets (>10M) and computational resources, while training-free approaches suffer from weak instruction comprehension.…
Autonomous racing serves as a critical benchmark for advancing autonomous vehicle technologies in challenging scenarios. Most traditional methods rely on complex vehicle dynamics models, posing significant challenges in modeling and computation. While reinforcement learning (RL) offers a promising a
Recently there has been growing interest in the use of aerial and satellite map data for autonomous vehicles, primarily due to its potential for significant cost reduction and enhanced scalability. Despite the advantages, aerial data also comes with challenges such as a sensor-modality gap and a vie
Large Language Models (LLMs) are increasingly used in decision-making scenarios that involve risk assessment, yet their alignment with human economic rationality remains unclear. In this study, we investigate whether LLMs exhibit risk preferences consistent with human expectations across different p
The efficacy of text embedding models in representing and retrieving information is crucial for many NLP applications, with performance significantly advanced by Large Language Models (LLMs). Despite this progress, existing benchmarks predominantly use general-purpose datasets, inadequately addressi
In this paper, fixed-time variable gain trajectory tracking control is designed for solving nonlinear unknown disturbance problems of 6-DOF manipulators. The designed control method comprises a fixed-time variable gain disturbance observer (FTVGDOB) and a fixed-time variable gain controller (FTVGC),
Long-form video understanding poses a significant challenge for video large language models (VideoLLMs) due to prohibitively high computational and memory demands. In this paper, We propose $\textbf{FlexSelect}$, a flexible and efficient token selection strategy for processing long videos. FlexSele…
Diffusion models have revolutionized generative modeling, enabling unprecedented realism in image and video synthesis.This success has sparked interest in leveraging their representations for visual understanding tasks. While recent works have explored this potential for image generation, the visual…
Multi-modal Large language models (MLLMs) show remarkable ability in video understanding. Nevertheless, understanding long videos remains challenging as the models can only process a finite number of frames in a single inference, potentially omitting crucial visual information. To address the challe…
In autonomous driving, accurately predicting occupancy and motion is crucial for safe navigation within dynamic environments. However, existing methods often suffer from difficulties in handling complex scenes and uncertainty arising from sensor data. To address these issues, we propose a new Gaussi…
Recent advancements in 3D Gaussian Splatting(3DGS) have significantly improved semantic scene understanding, enabling natural language queries to localize objects within a scene. However, existing methods primarily focus on embedding compressed CLIP features to 3D Gaussians, suffering from low objec
Learning from demonstration is a powerful method for robotic skill acquisition. However, the significant expense of collecting such action-labeled robot data presents a major bottleneck. Video data, a rich data source encompassing diverse behavioral and physical knowledge, emerges as a promising alt…
In this paper, we tackle the task of online video temporal grounding (OnVTG), which requires the model to locate events related to a given text query within a video stream. Unlike regular video temporal grounding, OnVTG requires the model to make predictions without observing future frames. As onlin…
This paper tackles the challenge of stereoscopic image rain removal by focusing on enhancing texture integrity and disparity consistency. Existing stereoscopic rain removal techniques often fall short due to 1) disruptions in texture coherence caused by complex rain streaks, and 2) inaccuracies in d…
In various robotic applications, understanding accurate object poses for robots is essential for high-precision tasks such as factory assembly or daily insertions. Tactile sensing, which compensates for visual information, offers rich texture-based or force-based data for object pose estimation. How
Recent advances in operator learning have produced two distinct approaches for solving partial differential equations (PDEs): attention-based methods offering point-level adaptability but lacking spectral constraints, and spectral-based methods providing domain-level continuity priors but limited in…
DETR introduces a simplified one-stage framework for scene graph generation (SGG) but faces challenges of sparse supervision and false negative samples. The former occurs because each image typically contains fewer than 10 relation annotations, while DETR-based SGG models employ over 100 relation qu…
The performance of large language models (LLMs) is closely tied to their training data, which can include copyrighted material or private information, raising legal and ethical concerns. Additionally, LLMs face criticism for dataset contamination and internalizing biases. To address these issues, th
Diffusion models have revitalized the image generation domain, playing crucial roles in both academic research and artistic expression. With the emergence of new diffusion models, assessing the performance of text-to-image models has become increasingly important. Current metrics focus on directly m…
The Zero-shot Composed Image Retrieval (ZSCIR) requires retrieving images that match the query image and the relative captions.Current methods focus on projecting the query image into the text feature space, subsequently combining them with features of query texts for retrieval. However, retrieving…
Articulated wheeled robots play a crucial role in the logistics industry. However, conventional tractor-driven articulated wheeled robots exhibit poor internal stability and are prone to jackknifing, while also consuming a significant amount of energy. By deploying distributed drives and coordinatin
Large language models (LLMs) demonstrate remarkable capabilities but face challenges from hallucinations, which typically arise from insufficient knowledge or context. While instructing LLMs to acknowledge knowledge limitations by responding with “I don’t know” appears promising, we find that models…
Current autonomous driving technology typically relies on high-precision (HD) maps to ensure safe, reliable, and accurate navigation in urban environments. While these maps provide essential road information, their creation and maintenance are costly, limiting their widespread application. To mitiga
Implicit reconstruction of ESDF (Euclidean Signed Distance Field) involves training a neural network to regress the signed distance from any point to the nearest obstacle, which has the advantages of lightweight storage and continuous querying. However, existing algorithms usually rely on conflictin
With Large Language Model (LLM) agents taking on more evaluation responsibilities in decision-making, it is essential to recognize their possible biases to guarantee fair and trustworthy AI-supported decisions. This study is the first to thoroughly examine the choice-supportive bias in LLM agents, a…
Legal Judgment Prediction (LJP) seeks to predict case outcomes given available case information, offering practical value for both legal professionals and laypersons. However, a key limitation of existing LJP models is their limited adaptability to statutory revisions. Current SOTA models are neithe…
Deep networks are prone to catastrophic forgetting during sequential task learning, i.e., losing the knowledge about old tasks upon learning new tasks. To this end, continual learning (CL) has emerged, whose existing methods focus mostly on regulating or protecting the parameters associated with the…
Visual instructions for long-horizon tasks are crucial as they intuitively clarify complex concepts and enhance retention across extended steps. Directly generating a series of images using text-to-image models without considering the context of previous steps results in inconsistent images, increa…
Large Language Models (LLMs)-based Multi-Agent Systems (MAS) exhibit remarkable problem-solving and task planning capabilities across diverse domains due to their specialized agentic roles and collaborative interactions. However, this also amplifies the severity of security risks under MAS attacks.
While multimodal large language models (MLLMs) have demonstrated extraordinary vision-language understanding capabilities, their abilities to solve instance-level visual-language problems beyond a single image warrant further exploration. To assess these unproven abilities of MLLMs, this paper propo…
3D reconstruction and simulation, although interrelated, have distinct objectives: reconstruction requires a flexible 3D representation that can adapt to diverse scenes, while simulation needs a structured representation to model motion principles effectively. This paper introduces the Mesh-adsorbed…
We present MeshLLM, a novel framework that leverages large language models (LLMs) to understand and generate text-serialized 3D meshes. Our approach addresses key limitations in existing methods, including the limited dataset scale when catering to LLMs' token length and the loss of 3D structural in…
Current wheeled bipedal robots face significant mobility challenges when traversing discontinuous terrain such as gaps and step-like obstacles, and suffer from substantial dynamic inefficiencies. This paper presents a hybrid self-reconfigurable wheel-legged dual-arm robot equipped with an active doc
We introduce NeRF-GS, a novel framework that jointly optimizes Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS). This framework leverages the inherent continuous spatial representation of NeRF to mitigate several limitations of 3DGS, including sensitivity to Gaussian initialization, li…
Zeolites are crystalline porous materials that have been widely utilized in petrochemical industries as well as sustainable chemistry areas. Synthesis of zeolites often requires small molecules termed Organic Structure Directing Agents (OSDAs), which are critical in forming the porous structure. Mol…
Semantic segmentation is a critical technique for effective scene understanding. Traditional RGB-T semantic segmentation models often struggle to generalize across diverse scenarios due to their reliance on pretrained models and predefined categories. Recent advancements in Visual Language Models (V
Recent advancements in 3D scene understanding have made significant strides in enabling interaction with scenes using open-vocabulary queries, particularly for VR/AR and robotic applications. Nevertheless, existing methods are hindered by rigid offline pipelines and the inability to provide precise
Recent advancements in 3D Gaussian Splatting have significantly improved the efficiency and quality of dense semantic SLAM. However, previous methods are generally constrained by limited-category pre-trained classifiers and implicit semantic representation, which hinder their performance in open-set
Multi-agent distributed collaborative mapping provides comprehensive and efficient representations for robots. However, existing approaches lack instance-level awareness and semantic understanding of environments, limiting their effectiveness for downstream applications. To address this issue, we pr
In recent years, there has been a surge of interest in open-vocabulary 3D scene reconstruction facilitated by visual language models (VLMs), which showcase remarkable capabilities in open-set retrieval tasks. Although the semantic ambiguity of existing point-wise feature maps is alleviated by open-v
In recent years, vision-language models (VLMs) have advanced open-vocabulary mapping, enabling mobile robots to simultaneously achieve environmental reconstruction and high-level semantic understanding. While integrated object cognition helps mitigate semantic ambiguity in point-wise feature maps, e
Text-guided image-to-image diffusion models excel in translating images based on textual prompts, allowing for precise and creative visual modifications. However, such a powerful technique can be misused for *spreading misinformation*, *infringing on copyrights*, and *evading content tracing*. This…
Automatic Valet Parking (AVP) has garnered significant attention from industry and academia due to its potential to enhance traffic efficiency, parking safety, and user experience. While AVP technologies have been successfully applied in standard parking scenarios with clear markings, real-world par
Shadow removal aims to restore the image content in shadowed regions. While deep learning-based methods have shown promising results, they still face key challenges: 1) uncontrolled removal of all shadows, or 2) controllable removal but heavily relies on precise shadow region masks. To address these
Large Language Models have demonstrated remarkable reasoning capability in complex textual tasks. However, multimodal reasoning, which requires integrating visual and textual information, remains a significant challenge. Existing visual-language models often struggle to effectively analyze and reaso…
Accurately modeling chemical reactions using Artificial Intelligence (AI) can accelerate discovery and development, especially in fields like drug design and material science. Although AI has made remarkable advancements in single molecule recognition, such as predicting molecular properties, the st…
Nowadays, numerous online platforms can be described as multi-modal heterogeneous networks (MMHNs), such as Douban's movie networks and Amazon's product review networks. Accurately categorizing nodes within these networks is crucial for analyzing the corresponding entities, which requires effective
Reconstructing dynamic roads from roadside traffic surveillance cameras is crucial for smart cities and digital twin applications. While the latest monocular depth estimation methods demonstrate strong performance, they exhibit instability in roadside scenarios. Existing reconstruction approaches fo
Controllable generation has achieved substantial progress in both 2D and 3D domains, yet current conditional generation methods still face limitations in describing detailed shape structures. Skeletons can effectively represent and describe object anatomy and pose. Unfortunately, past studies are of…
Topic evolution and stance dynamics are deeply intertwined in online social media, shaping the fragmentation and polarization of public discourse. Yet existing dynamic topic models and stance analysis approaches usually consider these processes in isolation, relying on abstractions that lack interpr
The ability to perform reliable long-horizon task planning is crucial for deploying robots in real-world environments. However, directly employing Large Language Models (LLMs) as action sequence generators often results in low success rates due to their limited reasoning ability for long-horizon emb
Navigation instruction generation (NIG), which provides interactive feedback and guidance to humans along a trajectory, is vital for developing embodied agents capable of human-machine communication and collaboration through natural language. Early data-driven methods directly map sequences of past…
Advances in talking-head animation based on Latent Diffusion Models (LDM) enable the creation of highly realistic, synchronized videos. These fabricated videos are indistinguishable from real ones, increasing the risk of potential misuse for scams, political manipulation, and misinformation. Hence,…
Recent advancements in state-of-the-art (SOTA) Large Language Model (LLM) agents, especially in multi-turn dialogue tasks, have been primarily driven by supervised fine-tuning and high-quality human feedback. However, as base LLM models continue to improve, acquiring meaningful human feedback has be…
Diffusion Transformers (DiT) are renowned for their impressive generative performance; however, they are significantly constrained by considerable computational costs due to the quadratic complexity in self-attention and the extensive sampling steps required. While advancements have been made in exp…
Tracking Any Point (TAP) in a video is a challenging computer vision problem with many demonstrated applications in robotics, video editing, and 3D reconstruction. Existing methods for TAP rely heavily on complex tracking-specific inductive biases and heuristics, limiting their generality and potent…
Reliable semantic segmentation of open environments is essential for intelligent systems, yet significant problems remain: 1) Existing RGB-T semantic segmentation models mainly rely on low-level visual features and lack high-level textual information, which struggle with accurate segmentation when c
Training Data Detection (TDD) is a task aimed at determining whether a specific data instance is used to train a machine learning model. In the computer security literature, TDD is also referred to as Membership Inference Attack (MIA). Given its potential to assess the risks of training data breach…
Video generation models are revolutionizing content creation, with image-to-video models drawing increasing attention due to their enhanced controllability, visual consistency, and practical applications. However, despite their popularity, these models rely on user-provided text and image prompts, a…
Building autonomous agents that can replicate human behavior in the realistic 3D world is a key step toward artificial general intelligence. This requires agents to be holistic goal achievers and to naturally adapt to environmental dynamics. In this work, we introduce ACTOR, an agent capable of perf…
Infants are capable of learning language, predominantly through speech and associations, in impoverished environments—a phenomenon known as the Poverty of the Stimulus (POS). Is this ability uniquely human, as an innate linguistic predisposition, or can it be empirically learned through potential li…
Image stitching in heavy occlusion scenarios faces the dual challenges of accurate alignment and occlusion removal. On one hand, occlusion causes the loss of key texture and structural information in the image. On the other hand, it affects the image’s integrity. Existing stitching methods perform w
In recent years, with the rapid development of Advanced Driver Assistance Systems (ADAS), the demand for the precise and efficient surround view stitching system has significantly increased. Traditional stitching methods perform well in small single-unit vehicles with stable camera poses. However, t
Underwater visual simultaneous localization and mapping (SLAM) faces critical challenges in light attenuation and degraded geometric consistency. Despite recent advances of visual SLAM in indoor and urban scenes, these approaches typically assume a clear medium and neglect medium-light interactions,…
Text-to-image generation has transformed content creation, yet precise visual text rendering remains challenging for generative models due to blurred glyphs, semantic inconsistencies, and limited style controllability. Current methods typically employ pre-rendered glyph images as conditional inputs,…
Space-limited U-shape bend is a safety-critical scenario that requires the high maneuverability of vehicles. However, due to the non-holonomic nature of the vehicle, it is difficult to perform flexible U-turns without intricate adjustments, which is detrimental to the efficient execution of tasks. T
Role-playing agents (RPAs) have attracted growing interest for their ability to simulate immersive and interactive characters. However, existing approaches primarily focus on static role profiles, overlooking the dynamic perceptual abilities inherent to humans. To bridge this gap, we introduce the c
Recent advancements in diffusion models have significantly improved video generation and editing capabilities. However, multi-grained video editing, which encompasses class-level, instance-level, and part-level modifications, remains a formidable challenge. The major difficulties in multi-grained ed…
Text-to-video generative models convert textual prompts into dynamic visual content, offering wide-ranging applications in film production, gaming, and education. However, their real-world performance often falls short of user expectations. One key reason is that these models have not been trained o…
Zero-shot learning (ZSL) aims to recognize unseen classes by transferring semantic knowledge from seen classes to unseen ones, guided by semantic information. To this end, existing works have demonstrated remarkable performance by utilizing global visual features from Convolutional Neural Networks (…
The traditional oscillators are limited by their material characteristics and structural configuration, exhibiting a low oscillation frequency and low output power under pressure input. This results in a slow locomotion speed for the robot. To address these limitations, this work presents a compact,
Lexical tones play a crucial role in Sino-Tibetan languages. However, current phonetic fieldwork relies on manual effort, resulting in substantial time and financial costs. This is especially challenging for the numerous endangered languages that are rapidly disappearing, often compounded by limited…
In this paper, we introduce the Financial-STS task, a financial domain-specific NLP task designed to measure the nuanced semantic similarity between pairs of financial narratives. These narratives originate from the financial statements of the same company but correspond to different periods, such a…
The fast-growing large scale language models are delivering unprecedented performance on almost all natural language processing tasks. However, the effectiveness of large language models are reliant on an exponentially increasing number of parameters. The overwhelming computation complexity incurs a…
We concentrate on a novel human-centric image synthesis task that is given only one reference facial photograph it is expected to generate specific individual images with diverse head positions poses facial expressions and illuminations in different contexts. To accomplish this goal we argue that ou…
"Recent work on image content manipulation based on vision-language pre-training models has been effectively extended to text-driven 3D scene editing. However, existing schemes for 3D scene editing still exhibit certain shortcomings, hindering their further interactive design. Such schemes typically…
Prominent solutions for medical image segmentation are typically tailored for automatic or interactive setups posing challenges in facilitating progress achieved in one task to another. This also necessitates separate models for each task duplicating both training time and parameters. To address abo…
Protein representation learning is a challenging task that aims to capture the structure and function of proteins from their amino acid sequences. Previous methods largely ignored the fact that not all amino acids are equally important for protein folding and activity. In this article we propose a n…
We study the patent phrase similarity inference task, which measures the semantic similarity between two patent phrases. As patent documents employ legal and highly technical language, existing semantic textual similarity methods that use localized contextual information do not perform satisfactoril…
"Instruction generation is a vital and multidisciplinary research area with broad applications. Existing instruction generation models are limited to generating instructions in a single style from a particular dataset, and the style and content of generated instructions cannot be controlled. Moreove…
Text-video retrieval is a critical multi-modal task to find the most relevant video for a text query. Although pretrained models like CLIP have demonstrated impressive potential in this area, the rising cost of fully finetuning these models due to increasing model size continues to pose a problem. T…
Recovering the foreground color and opacity/alpha matte from a single image (i.e., image matting) is a challenging and ill-posed problem where data priors play a critical role in achieving precise results. Traditional methods generally predict the alpha matte and then extract the foreground through…
In recent years, 3D surround view systems have attracted a lot of attention in the field of advanced driver assistance systems (ADAS). However, the foundational assumption of unchanging camera poses in traditional 3D surround view systems, which is designed for single-unit vehicles, results in a fai…
Federated Learning (FL) is commonly used to collaboratively train models with privacy preservation. In this paper, we found out that the popular diffusion models have introduced a new vulnerability to FL, which brings serious privacy threats. Despite stringent data management measures, attackers can…
Scene flow estimation determines a scene’s 3D motion field, by predicting the motion of points in the scene, especially for aiding tasks in autonomous driving. Many networks with large-scale point clouds as input use voxelization to create a pseudo-image for real-time running. However, the voxelizat…
Many robot manipulation tasks can be framed as geometric reasoning tasks, where an agent must be able to precisely manipulate an object into a position that satisfies the task from a set of initial conditions. Often, task success is defined based on the relationship between two objects - for instanc…
"In this paper, we delve into Blind Image Decomposition (BID) tailored for real-world scenarios, aiming to uniformly recover images from diverse, unknown weather combinations and intensities. Our investigation uncovers one inherent gap between the controlled lab settings and the complex real-world e…
Recent LLM-driven visual agents mainly focus on solving image-based tasks, which limits their ability to understand dynamic scenes, making it far from real-life applications like guiding students in laboratory experiments and identifying their mistakes. Hence, this paper explores DoraemonGPT, a comp…
Large Language Models (LLMs) are widely used for writing economic analysis reports or providing financial advice, but their ability to understand economic knowledge and reason about potential results of specific economic events lacks systematic evaluation. To address this gap, we propose a new datas…
Detecting hallucinations in large language model (LLM) outputs is pivotal, yet traditional fine-tuning for this classification task is impeded by the expensive and quickly outdated annotation process, especially across numerous vertical domains and in the face of rapid LLM advancements. In this stud…
Generalizable NeRF can directly synthesize novel views across new scenes eliminating the need for scene-specific retraining in vanilla NeRF. A critical enabling factor in these approaches is the extraction of a generalizable 3D representation by aggregating source-view features. In this paper we pro…
Generalizable 3D Gaussian splitting (3DGS) can reconstruct new scenes from sparse-view observations in a feed-forward inference manner, eliminating the need for scene-specific retraining required in conventional 3DGS. However, existing methods rely heavily on epipolar priors, which can be unreliable…
In-Context Learning (ICL) and Instruction Tuning (IT) are two primary paradigms of adopting Large Language Models (LLMs) to downstream applications. However, they are significantly different. In ICL, a set of demonstrations is provided at the inference time, but the LLM’s parameters are not updated.…
Point cloud registration is essential in computer vision and robotics. Recently, transformer-based methods have achieved advanced point cloud registration performance. However, the standard attention mechanism utilized in these methods considers many low-relevance points, and it has difficulty focus…
3D reconstruction methods such as Neural Radiance Fields (NeRFs) are capable of optimizing high-quality 3D representation from images. However, NeRF is limited by the requirement for a large number of multi-view images, making its application to real-world scenarios challenging. In this work, we pro…
To process contexts with unlimited length using Large Language Models (LLMs), recent studies explore hierarchically managing the long text. Only several text fragments are taken from the external memory and passed into the temporary working memory, i.e., LLM’s context window. However, existing appro…
Video diffusion models have made substantial progress in various video generation applications. However, training models for long video generation tasks require significant computational and data resources, posing a challenge to developing long video diffusion models. This paper investigates a strai…
"Creating digital avatars from textual prompts has long been a desirable yet challenging task. Despite the promising results achieved with 2D diffusion priors, current methods struggle to create high-quality and consistent animated avatars efficiently. Previous animatable head models like FLAME have…
Prevalent human-object interaction (HOI) detection approaches typically leverage large-scale visual-linguistic models to help recognize events involving humans and objects. Though promising, models trained via contrastive learning on text-image pairs often neglect mid/low-level visual cues and strug…
Images produced by diffusion models are increasingly popular in digital artwork and visual marketing. However, such generated images might replicate content from existing ones and pose the challenge of content originality. Existing Image Copy Detection (ICD) models, though accurate in detecting hand…
Semantic segmentation in bird's eye view (BEV) plays a crucial role in autonomous driving. Previous methods usually follow an end-to-end pipeline directly predicting the BEV segmentation map from monocular RGB inputs. However the challenge arises when the RGB inputs and BEV targets from distinct per…
Previous efforts using frozen Large Language Models (LLMs) for visual understanding, via image captioning or image-text retrieval tasks, face challenges when dealing with complex multimodal scenarios. In order to enhance the capabilities of Multimodal Large Language Models (MLLM) in comprehending th…
3D decision-critical tasks urgently require research on explanations to ensure system reliability and transparency. Extensive explanatory research has been conducted on 2D images, but there is a lack in the 3D field. Furthermore, the existing explanations for 3D models are post-hoc and can be mislea…
We study the zero-shot Composed Image Retrieval (ZS-CIR) task which is to retrieve the target image given a reference image and a description without training on the triplet datasets. Previous works generate pseudo-word tokens by projecting the reference image features to the text embedding space. H…
Recently the dense Simultaneous Localization and Mapping (SLAM) based on neural implicit representation has shown impressive progress in hole filling and high-fidelity mapping. Nevertheless, existing methods either heavily rely on known scene bounds or suffer inconsistent reconstruction due to drift…
Autonomous systems need to process large-scale sparse and irregular point clouds with limited compute resources. Consequently it is essential to develop LiDAR perception methods that are both efficient and effective. Although naively enlarging 3D kernel size can enhance performance it will also lead…
We introduce a framework for online learning from a single continuous video stream - the way people and animals learn without mini-batches data augmentation or shuffling. This poses great challenges given the high correlation between consecutive video frames and there is very little prior work on it…
Collaborative mapping aids agents in achieving an efficient and comprehensive understanding of their environment. Recently, there has been growing interest in using neural networks as maps to represent functions that implicitly define the geometric features of a scene. However, existing implicit map
We present a Multi-Instance Generation (MIG) task simultaneously generating multiple instances with diverse controls in one image. Given a set of predefined coordinates and their corresponding descriptions the task is to ensure that generated instances are accurately at the designated locations and…
DETR accomplishes end-to-end object detection through iteratively generating multiple object candidates based on image features and promoting one candidate for each ground-truth object. The traditional training procedure using one-to-one supervision in the original DETR lacks direct supervision for…
Sign language understanding has made significant strides; however, there is still no viable solution for generating sign sequences directlyfrom entire spoken content, e.g., text or speech. In this paper, we propose a unified framework for continuous sign language production, easing communication bet…
Current vision models typically maintain a fixed correspondence between their representation structure and image space. Each layer comprises a set of tokens arranged “on-the-grid,” which biases patches or tokens to encode information at a specific spatio(-temporal) location. In this work we present…
"Visual acoustic matching (VAM) is pivotal for enhancing the immersive experience, and the task of dereverberation is effective in improving audio intelligibility. Existing methods treat each task independently, overlooking the inherent reciprocity between them. Moreover, these methods depend on pai…
"Navigation instruction generation, which requires embodied agents to describe the navigation routes, has been of great interest in robotics and human-computer interaction. Existing studies directly map the sequence of 2D perspective observations to route descriptions. Though straightforward, they o…
We investigate a fundamental aspect of machine vision: the measurement of features by revisiting clustering one of the most classic approaches in machine learning and data analysis. Existing visual feature extractors including ConvNets ViTs and MLPs represent an image as rectangular regions. Though…
"This work addresses a new challenge of understanding human nonverbal interaction in social contexts. Nonverbal signals pervade virtually every communicative act. Our gestures, facial expressions, postures, gaze, even physical appearance all convey messages, without anything being said. Despite thei…
Environment representations endowed with sophisticated semantics are pivotal for facilitating seamless interaction between robots and humans, enabling them to effectively carry out various tasks. Open-vocabulary representation, powered by Visual-Language models (VLMs), possesses inherent advantages,