26 accepted papers
Traditional on-policy Reinforcement Learning with Verifiable Rewards (RLVR) frameworks suffer from experience waste and reward homogeneity, which directly hinders learning efficiency on difficult samples during large language models post-training. In this paper, we introduce Batch Adaptation Policy…
A core challenge for embodied agents is the ``semantic-to-physical gap"—the difficulty of mapping symbolic reasoning to precise execution. While Vision-Language Models (VLMs) enhance agent task planning, they often fail in problem classes requiring accurate alignment between functional geometry and
Real-world physical sensing exhibits complex, heterogeneous noise patterns that deviate significantly from idealized simulation, posing a fundamental bottleneck for sim-to-real transfer. Existing sensor modelings typically treat depth noise as a monolithic black-box process, overlooking the distinct…
Growing renewable penetration introduces substantial uncertainty into power system operations, necessitating frequent adaptation of dispatch objectives and constraints and challenging expertise-intensive, near-real-time modeling workflows. Large Language Models (LLMs) provide a promising avenue for …
Inference-time scaling has emerged as a critical avenue for enhancing Large Language Model performance, yet real-world deployment is bound by strict computational budgets. In this work, we formulate inference budget allocation as a global constrained optimization problem governed by economic princip…
Joint rendering and deformation of mesh and 3D Gaussian Splatting (3DGS) have significant value as both representations offer complementary advantages for graphics applications. However, due to differences in representation and rendering pipelines, existing studies render meshes and 3DGS separately,
In robotic visuomotor policy learning, diffusion-based models have achieved significant success in improving the accuracy of action trajectory generation compared to traditional autoregressive models. However, they suffer from inefficiency due to multiple denoising steps and limited flexibility from…
Safe Reinforcement Learning (RL) is crucial for achieving high performance while ensuring safety in real-world applications. However, the complex interplay of multiple uncertainty sources in real environments poses significant challenges for interpretable risk assessment and robust decision-making.…
Low-Light Image Enhancement (LLIE) is crucial for improving image quality and visual analysis. This study proposes MLSwinTNet, an LLIE network based on the Swin Transformer. The core MLSwinT module adopts a UNet-like design, integrating a dual-branch feature extraction module and a multi-level featu…
This paper addresses the inherent inference latency challenges associated with deploying multimodal large language models (MLLM) in quadruped vision-language-action (QUAR-VLA) tasks. Our investigation reveals that conventional parameter reduction techniques ultimately impair the performance of the l
Learning-based garment prediction presents an appealing alternative to physics-based methods owing to its high efficiency. However, the predicted garments can exhibit noticeable penetrations into the body. Many collision-handling methods operate in the point domain, which has an inherent limitation…
Despite impressive advancements in Visual-Language Models (VLMs) for multi-modal tasks, their reliance on RGB inputs limits precise spatial understanding. Existing methods for integrating spatial cues, such as point clouds or depth, either require specialized sensors or fail to effectively exploit d…
Diffusion policies have shown promise in learning complex behaviors from demonstrations, particularly for tasks requiring precise control and long-term planning. However, they face challenges in robustness when encountering distribution shifts. This paper explores improving diffusion-based imitation…
Although multi-agent reinforcement learning (MARL) has shown its success across diverse domains, extending its application to large-scale real-world systems still faces significant challenges. Primarily, the high complexity of real-world environments exacerbates the credit assignment problem, substa…
Recent advancements in Large Language Models (LLMs) and Reinforcement Learning (RL) have shown significant promise in decision-making tasks. Nevertheless, for large-scale industrial decision problems, both approaches face distinct challenges: LLMs lack real-time long-sequence decision-making capabil…
Multimodal Sentiment Analysis (MSA) has attracted widespread research attention recently. Most MSA studies are based on the assumption of modality completeness. However, many inevitable factors in real-world scenarios lead to uncertain missing modalities, which invalidate the fixed multimodal fusion…
Multimodal sentiment analysis (MSA) aims to understand human sentiment through multimodal data. Most MSA efforts are based on the assumption of modality completeness. However in real-world applications some practical factors cause uncertain modality missingness which drastically degrades the model's…
Vision-based 3D semantic scene completion (SSC) describes autonomous driving scenes through 3D volume representations. However, the occlusion of invisible voxels by scene surfaces poses challenges to current SSC methods in hallucinating refined 3D geometry. This letter proposes HybridOcc, a hybrid 3
Multimodal Sentiment Analysis (MSA) is an important research area that aims to understand and recognize human sentiment through multiple modalities. The complementary information provided by multimodal fusion promotes better sentiment analysis compared to utilizing only a single modality. Neverthele…
With the increasing penetration of inverter-based renewable energy resources, deep reinforcement learning (DRL) has been proposed as one of the most promising solutions to realize real-time and autonomous control for future carbon-neutral power systems. In particular, DRL-based frequency control app…
There is a growing demand of automatically synthesizing co-speech gestures for virtual characters. However, it remains a challenge due to the complex relationship between input speeches and target gestures. Most existing works focus on predicting the next gesture that fits the data best, however, su…
Although CNN-based and Transformer-based detectors have made impressive improvements in 3D object detection, these two network paradigms suffer from the interference of insufficient receptive field and local detail weakening, which significantly limits the feature extraction performance of the backb…
Value type of the slots can provide lots of useful information for DST tasks. However, it has been ignored in most previous works. In this paper, we propose a new framework for DST task based on these value types. Firstly, we extract the type of token from each turn. Specifically, we divide the slot…
Collecting dialogue data with domain-slot-value labels for dialogue state tracking (DST) could be a costly process. In this paper, we propose a novel framework based on domain-slot related description to tackle the challenge of few-shot cross-domain DST. Specifically, we design an extraction module…
Decarbonization of global power systems significantly increases the operational uncertainty and modeling complexity that drive the necessity of widely exploiting cutting-edge Deep Reinforcement Learning (DRL) technologies to realize adaptive and real-time emergency control, which is the last resort…
Person re-identification is one of the key issues in both machine learning and video monitor application. In particular, defining an appropriate distance metric between the person images is very important. Existing metric learning approaches used in person re-identification either learn a single mea…