53 accepted papers
Recent advances in few-step generative models (typically $1$-$8$ steps), such as consistency models, have yielded impressive performance. However, their broader adoption is hindered by significant challenges, including substantial computational overhead, the reliance on complex multi-component loss…
In standard causal attention, each token's query, key, and value (QKV) are static and encode only preceding context. We introduce CAuSal aTtention with Lookahead kEys (CASTLE), an attention mechanism that continually updates each token's keys as the context unfolds. We term these updated keys lookah…
Recent text-to-video diffusion models can synthesize visually compelling clips from natural language prompts. However, practical applications increasingly demand long-form videos with evolving narratives and persistent identity. A common solution is autoregressive generation, where the video is prod…
Analytical diffusion models offer a mathematically transparent path to generative modeling by formulating the denoising score as an empirical-Bayes posterior mean. However, this interpretability comes at a prohibitive cost: the standard formulation necessitates a full-dataset scan at every timestep,…
With the increasing presence of service robots and autonomous vehicles in human environments, navigation systems need to evolve beyond simple destination reach to incorporate social awareness. This paper introduces GSON, a novel group-based social navigation framework that leverages Large Multimodal…
Batch inference for agentic workloads stresses the GPU key–value (KV) cache in a sustained and cumulative manner, often causing severe throughput degradation well before memory capacity is exhausted. We identify this phenomenon as middle-phase thrashing, a previously under-characterized pathology in…
Missing modalities present a fundamental challenge in multimodal models, often causing catastrophic performance degradation. Our observations suggest that this fragility stems from an imbalanced learning process, where the model develops an implicit preference for certain modalities, leading to the…
Unified Multimodal Models (UMMs) are often constrained by the pre-training of their visual generation components, which typically relies on inefficient paradigms and scarce, high-quality text-image paired data. In this paper, we systematically analyze pre-training recipes for UMM visual generation a
Reinforcement learning (RL) has recently become the core paradigm for aligning and strengthening large language models (LLMs). Yet, applying RL in off-policy settings—where stale data from past policies are used for training—improves sample efficiency, but remains challenging: policy entropy decline…
Recent advances in large multi-modal generative models have demonstrated impressive capabilities in multi-modal generation, including image and video generation. These models are typically built upon multi-step frameworks like diffusion and flow matching, which inherently limits their inference effi…
Reinforcement learning (RL) is crucial for aligning Vision-Language Models (VLMs), but its practical application is hampered by significant system-level bottlenecks. The typical RL pipeline, encompassing data loading, inference-based rollouts, and model updates, suffers from severe inefficiencies wh…
To identify objects beyond predefined categories, open-vocabulary aerial object detection (OVAD) leverages the zero-shot capabilities of visual-language models (VLMs) to generalize from base to novel categories. Existing approaches typically utilize self-learning mechanisms with weak text supervisio
With the rapid advancement of generative models, highly realistic image synthesis has posed new challenges to digital security and media credibility. Although AI-generated image detection methods have partially addressed these concerns, a substantial research gap remains in evaluating their performa…
As a potential application of Vehicle-to-Everything (V2X) communication, multi-agent collaborative perception has achieved significant success in 3D object detection. While these methods have demonstrated impressive results on standard benchmarks, the robustness of such approaches in the face of com…
Recent advancements in dataset distillation have demonstrated the significant benefits of employing soft labels generated by pre-trained teacher models. In this paper, we introduce a novel perspective by emphasizing the full utilization of labels. We first conduct a comprehensive comparison…
With the increasing presence of service robots and autonomous vehicles in human environments, navigation systems need to evolve beyond simple destination reach to incorporate social awareness. This paper introduces <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/199
Achieving Artificial General Intelligence (AGI) requires AI agents that can not only make strategic decisions but also engage in flexible and meaningful communication. Inspired by Wittgenstein's language game theory, we propose that language agents can learn through in-context interaction rather tha…
Natural language chain-of-thought (N-CoT) and Program chain-of-thought (P-CoT) have emerged as two primary paradigms for large language models (LLMs) to solve mathematical reasoning problems. Current research typically endeavors to achieve unidirectional enhancement: P-CoT enhanced N-CoT or N-CoT en
Human keypoint detection is fundamental in computer vision, with applications in pose estimation and action recognition. However, existing evaluation metrics (e.g., OKS, PCP, PDJ) rely on human-annotated ground truth, a labor-intensive process that increases costs, limits scalability. To address thi…
Crime prediction (CP) plays a pivotal role in urban analytics, contributing significantly to personal safety and societal stability. Unlike conventional time series forecasting, CP faces unique difficulties due to the inherent sparsity of crime incidents, particularly within small spatial regions an…
Traditional recurrent neural network architectures, such as long short-term memory neural networks (LSTM), have historically held a prominent role in time series forecasting (TSF) tasks. While the recently introduced sLSTM for Natural Language Processing (NLP) introduces exponential gating and memor…
Large-scale deep neural networks (DNNs), such as large language models, have gained immense popularity due to their outstanding performance across various tasks. However, their application in resource-constrained scenarios faces significant challenges due to the high computational costs and memory u…
Backdoor attacks pose serious security threats to deep neural networks (DNNs). Backdoored models make arbitrarily (targeted) incorrect predictions on inputs containing well-designed triggers, while behaving normally on clean inputs. Prior researches have explored the invisibility of backdoor trigger…
"Collaborative perception has received widespread attention recently since it enhances the perception ability of autonomous vehicles via inter-agent information sharing. However, the performance of existing systems is hindered by the unavoidable collaboration noises, which induce feature-level spati…
Decentralized federated learning (DFL) facilitates collaborative model training across multiple connected clients without a central coordination server thereby avoiding the single point of failure in traditional centralized federated learning (CFL). However DFL exhibits heightened susceptibility to…
Collaborative perception enhances perception performance by enabling autonomous vehicles to exchange complementary information. Despite its potential to revolutionize the mobile industry challenges in various environments such as communication bandwidth limitations localization errors and informatio…
Data, the seminal opportunity and challenge in modern machine learning, currently constrains the scalability of representation learning and impedes the pace of model evolution. In this work, we investigate the efficiency properties of data from both optimization and generalization perspectives. Our…
Backdoor defense is crucial to ensure the safety and robustness of machine learning models when under attack. However, most existing methods specialize in either the detection or removal of backdoors, but seldom both. While few works have addressed both, these methods rely on strong assumptions or e…
One way to enhance the reasoning capability of Large Language Models (LLMs) is to conduct Supervised Fine-Tuning (SFT) using Chain-of-Thought (CoT) annotations. This approach does not show sufficiently strong generalization ability, however, because the training only relies on the given CoT data. In…
In this paper, we propose **R**$^3$: Learning **R**easoning through **R**everse Curriculum **R**einforcement Learning (RL), a novel method that employs only outcome supervision to achieve the benefits of process supervision for large language models. The core challenge in applying RL to complex reas…
Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, garnering significant attention from both academia and industry. However, enhancing the performance of LLMs typically requires scaling up model sizes or fine-tuning with additional datasets, which results…
With the rapid development of intelligent transportation system applications, a tremendous amount of multi-view video data has emerged to enhance vehicle perception. However, performing video analytics efficiently by exploiting the spatial-temporal redundancy from video data remains challenging. Acc…
The recent flourish of deep learning on various tasks is largely accredited to the rich and high-quality labeled data. Nonetheless, collecting sufficient labeled samples is not very practical for many real applications. Few-shot Learning (FSL) provides a promising solution that allows a model to lea…
The performance of video frame interpolation is inherently correlated with the ability to handle motion in the input scene. Even though previous works recognize the utility of asynchronous event information for this task, they ignore the fact that motion may or may not result in blur in the input vi…
Exploration is one of the main challenges in Reinforcement Learning (RL), especially in environments with sparse rewards. Learning from Demonstrations (LfD) is a promising approach to solving this problem by leveraging expert demonstrations. However, expert demonstrations of high quality are usuall…
Mode decomposition methods are the current workhorse for the analysis of non-stationary signals. However, current attempts at these methods mainly focus on improving accuracy, leaving computational efficiency untouched. To this end, we leverage the neural mode decomposition technique and propose an…
Face recognition service providers protect face privacy by extracting compact and discriminative facial features (representations) from images, and storing the facial features for real-time recognition. However, such features can still be exploited to recover the appearance of the original face by b…
Multi-agent collaborative perception as a potential application for vehicle-to-everything communication could significantly improve the perception performance of autonomous vehicles over single-agent perception. However, several challenges remain in achieving pragmatic information sharing in this em…
Trajectory optimization (TO) combined with whole-body control (WBC) have been a widely accepted approach for dynamic gait control of quadruped robots. However, there are still open issues in this framework, one is the lack of a unified description of intrinsic inter-limb coordination for wide range
Transferability of adversarial examples is critical for black-box deep learning model attacks. While most existing studies focus on enhancing the transferability of untargeted adversarial attacks, few of them studied how to generate transferable targeted adversarial examples that can mislead models…
Promoting behavioural diversity is of critical importance in multi-agent reinforcement learning, since it helps the agent population maintain robust performance when encountering unfamiliar opponents at test time, or, when the game is highly non-transitive in the strategy space (e.g., Rock-Paper-Sc…
"Traditional frame-based cameras inevitably suffer from motion blur due to long exposure times. As a kind of bio-inspired camera, the event camera records the intensity changes in an asynchronous way with high temporal resolution, providing valid image degradation information within the exposure tim…
Federated learning (FL) is a privacy-preserving distributed machine learning paradigm that enables multiple clients to collaboratively train statistical models without disclosing raw training data. However, the inaccessible local training data and uninspectable local training process make FL suscept…
RGB-D salient object detection (SOD) is usually formulated as a problem of classification or regression over two modalities, i.e., RGB and depth. Hence, effective RGB-D feature modeling and multi-modal feature fusion both play a vital role in RGB-D SOD. In this paper, we propose a depth-sensitive RG…
In active visual tracking, it is notoriously difficult when distracting objects appear, as distractors often mislead the tracker by occluding the target or bringing a confusing appearance. To address this issue, we propose a mixed cooperative-competitive multi-agent game, where a target and multiple…
Designing a lightweight semantic segmentation network often requires researchers to find a trade-off between performance and speed, which is always empirical due to the limited interpretability of neural networks. In order to release researchers from these tedious mechanical trials, we propose a Gra…
Visual Active Tracking (VAT) aims at following a target object by autonomously controlling the motion system of a tracker given visual observations. Previous work has shown that the tracker can be trained in a simulator via reinforcement learning and deployed in real-world scenarios. However, during…
We consider the problem of multi-agent reinforcement learning (MARL) in video game AI, where the agents are located in a spatial grid-world environment and the number of agents varies both within and across episodes. The challenge is to flexibly control an arbitrary number of agents while achieving…
We propose a novel algorithmic framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-gradient (VMOR-HPE) method with a global convergence guarantee for the maximal monotone operator inclusion problem. Its iteration complexities and local linear convergence rate are provided, which theoreti…
We study active object tracking, where a tracker takes as input the visual observation (i.e. frame sequence) and produces the camera control signal (e.g., move forward, turn left, etc). Conventional methods tackle the tracking and the camera control separately, which is challenging to tune jointly.…
We consider deep policy learning with only batched historical trajectories. The main challenge of this problem is that the learner no longer has a simulator or ``environment oracle'' as in most reinforcement learning settings. To solve this problem, we propose a monotonic advantage reweighted imitat…
In this work we propose a new automatic image annotation model, dubbed diverse and distinct image annotation (D2IA). The generative model D2IA is inspired by the ensemble of human annotations, which create semantically relevant, yet distinct and diverse tags. In D2IA, we generate a relevant and dist…