Guang Chen

Ruiqi Zhang, Jing Hou, Florian Walter et al. · berkeley

Reinforcement Learning (RL) is a potent tool for sequential decision-making and has achieved performance surpassing human capabilities across many challenging real-world tasks. As the extension of RL in the multi-agent system domain, multi-agent RL (MARL) not only need to learn the control policy but also requires consideration regarding interactions with all other agents in the environment, mutual influences among different system components, and the distribution of computational resources. This augments the complexity of algorithmic design and poses higher requirements on computational resources. Simultaneously, simulators are crucial to obtain realistic data, which is the fundamentals of RL. In this paper, we first propose a series of metrics of simulators and summarize the features of existing benchmarks. Second, to ease comprehension, we recall the foundational knowledge and then synthesize the recently advanced studies of MARL-related autonomous driving and intelligent transportation systems. Specifically, we examine their environmental modeling, state representation, perception units, and algorithm design. Conclusively, we discuss open challenges as well as prospects and opportunities. We hope this paper can help the researchers integrate MARL technologies and trigger more insightful ideas toward the intelligent and autonomous driving.

Zehan Zheng, Danni Wu, Ruisi Lu et al.

In recent years, there has been a significant increase in focus on the interpolation task of computer vision. Despite the tremendous advancement of video interpolation, point cloud interpolation remains insufficiently explored. Meanwhile, the existence of numerous nonlinear large motions in real-world scenarios makes the point cloud interpolation task more challenging. In light of these issues, we present NeuralPCI: an end-to-end 4D spatio-temporal Neural field for 3D Point Cloud Interpolation, which implicitly integrates multi-frame information to handle nonlinear large motions for both indoor and outdoor scenarios. Furthermore, we construct a new multi-frame point cloud interpolation dataset called NL-Drive for large nonlinear motions in autonomous driving scenes to better demonstrate the superiority of our method. Ultimately, NeuralPCI achieves state-of-the-art performance on both DHB (Dynamic Human Bodies) and NL-Drive datasets. Beyond the interpolation task, our method can be naturally extended to point cloud extrapolation, morphing, and auto-labeling, which indicates its substantial potential in other domains. Codes are available at https://github.com/ispc-lab/NeuralPCI.

Speed Zhu, Jianwei Cai, Guang Chen et al.

Recent reasoning-first models (e.g., OpenAI o1, DeepSeek R1) have spurred a resurgence of interest in RLVR. Nevertheless, advances are dominated by mathematics (e.g., AIME), with competitive-programming code generation underexplored and data curation receiving less attention than RL algorithm design. We investigate how to construct RLVR datasets (i.e., RL prompts) and present practical training techniques that yield strong performance on competitive-programming code generation. Our pipeline begins with supervised fine-tuning (SFT) distilled from strong open-source models, augmented with general-purpose and reasoning-intensive data. RL then follows a two-stage process with executable, testcase-driven rewards: first, training on a large, uniformly distributed set of competitive-programming problems using Group Relative Policy Optimization (GRPO) with 8 rollouts per prompt and a relatively short response-generation window (e.g., 32k during SFT and 24k in this stage) to expand entropy and mitigate repetition and truncation; second, we perform \textbf{Pre-GRPO}: updating on a small, high-quality set of challenging problems with a large rollout budget (64 rollouts per prompt) under a hard-focus curriculum that continuously retains the most difficult instances throughout training. We implement our method on Qwen2.5-32B and evaluate on LeetCode and Codeforces weekly contests to avoid data leakage. The resulting model achieves state-of-the-art performance among models of similar scale and is comparable to leading systems such as DeepSeek v3.1 and Doubao-1.5-Thinking. We also examine scaling trends and observe strong RL scaling on an internal large-scale MoE model. Our study distills concise best practices for data curation, entropy expansion, and curriculum design in RLVR for competitive-programming code generation.

Lu Xu, Sijie Zhu, Chunyuan Li et al.

The emerging video LMMs (Large Multimodal Models) have achieved significant improvements on generic video understanding in the form of VQA (Visual Question Answering), where the raw videos are captured by cameras. However, a large portion of videos in real-world applications are edited videos, \textit{e.g.}, users usually cut and add effects/modifications to the raw video before publishing it on social media platforms. The edited videos usually have high view counts but they are not covered in existing benchmarks of video LMMs, \textit{i.e.}, ActivityNet-QA, or VideoChatGPT benchmark. In this paper, we leverage the edited videos on a popular short video platform, \textit{i.e.}, TikTok, and build a video VQA benchmark (named EditVid-QA) covering four typical editing categories, i.e., effect, funny, meme, and game. Funny and meme videos benchmark nuanced understanding and high-level reasoning, while effect and game evaluate the understanding capability of artificial design. Most of the open-source video LMMs perform poorly on the EditVid-QA benchmark, indicating a huge domain gap between edited short videos on social media and regular raw videos. To improve the generalization ability of LMMs, we collect a training set for the proposed benchmark based on both Panda-70M/WebVid raw videos and small-scale TikTok/CapCut edited videos, which boosts the performance on the proposed EditVid-QA benchmark, indicating the effectiveness of high-quality training data. We also identified a serious issue in the existing evaluation protocol using the GPT-3.5 judge, namely a "sorry" attack, where a sorry-style naive answer can achieve an extremely high rating from the GPT judge, e.g., over 4.3 for correctness score on VideoChatGPT evaluation protocol. To avoid the "sorry" attacks, we evaluate results with GPT-4 judge and keyword filtering. The dataset is released at https://github.com/XenonLamb/EditVid-QA.

Sanqing Qu, Guang Chen, Zhijun Li et al.

Weakly-supervised temporal action localization aims to localize action instances temporal boundary and identify the corresponding action category with only video-level labels. Traditional methods mainly focus on foreground and background frames separation with only a single attention branch and class activation sequence. However, we argue that apart from the distinctive foreground and background frames there are plenty of semantically ambiguous action context frames. It does not make sense to group those context frames to the same background class since they are semantically related to a specific action category. Consequently, it is challenging to suppress action context frames with only a single class activation sequence. To address this issue, in this paper, we propose an action-context modeling network termed ACM-Net, which integrates a three-branch attention module to measure the likelihood of each temporal point being action instance, context, or non-action background, simultaneously. Then based on the obtained three-branch attention values, we construct three-branch class activation sequences to represent the action instances, contexts, and non-action backgrounds, individually. To evaluate the effectiveness of our ACM-Net, we conduct extensive experiments on two benchmark datasets, THUMOS-14 and ActivityNet-1.3. The experiments show that our method can outperform current state-of-the-art methods, and even achieve comparable performance with fully-supervised methods. Code can be found at https://github.com/ispc-lab/ACM-Net

Can Zhang, Yuexian Zou, Guang Chen et al.

Efficiently modeling dynamic motion information in videos is crucial for action recognition task. Most state-of-the-art methods heavily rely on dense optical flow as motion representation. Although combining optical flow with RGB frames as input can achieve excellent recognition performance, the optical flow extraction is very time-consuming. This undoubtably will count against real-time action recognition. In this paper, we shed light on fast action recognition by lifting the reliance on optical flow. Our motivation lies in the observation that small displacements of motion boundaries are the most critical ingredients for distinguishing actions, so we design a novel motion cue called Persistence of Appearance (PA). In contrast to optical flow, our PA focuses more on distilling the motion information at boundaries. Also, it is more efficient by only accumulating pixel-wise differences in feature space, instead of using exhaustive patch-wise search of all the possible motion vectors. Our PA is over 1000x faster (8196fps vs. 8fps) than conventional optical flow in terms of motion modeling speed. To further aggregate the short-term dynamics in PA to long-term dynamics, we also devise a global temporal fusion strategy called Various-timescale Aggregation Pooling (VAP) that can adaptively model long-range temporal relationships across various timescales. We finally incorporate the proposed PA and VAP to form a unified framework called Persistent Appearance Network (PAN) with strong temporal modeling ability. Extensive experiments on six challenging action recognition benchmarks verify that our PAN outperforms recent state-of-the-art methods at low FLOPs. Codes and models are available at: https://github.com/zhang-can/PAN-PyTorch.

Haoyu Fu, Diankun Zhang, Zongchuang Zhao et al.

Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning. However, applying online reinforcement learning to VLA models in autonomous driving is hindered by inefficient exploration in continuous action spaces. To overcome this limitation, we propose MindDrive, a VLA framework comprising a large language model (LLM) with two distinct sets of LoRA parameters. The one LLM serves as a Decision Expert for scenario reasoning and driving decision-making, while the other acts as an Action Expert that dynamically maps linguistic decisions into feasible trajectories. By feeding trajectory-level rewards back into the reasoning space, MindDrive enables trial-and-error learning over a finite set of discrete linguistic driving decisions, instead of operating directly in a continuous action space. This approach effectively balances optimal decision-making in complex scenarios, human-like driving behavior, and efficient exploration in online reinforcement learning. Using the lightweight Qwen-0.5B LLM, MindDrive achieves Driving Score (DS) of 78.04 and Success Rate (SR) of 55.09% on the challenging Bench2Drive benchmark. To the best of our knowledge, this is the first work to demonstrate the effectiveness of online reinforcement learning for the VLA model in autonomous driving.

Sanqing Qu, Guang Chen, Dan Xu et al.

Online action detection is a task with the aim of identifying ongoing actions from streaming videos without any side information or access to future frames. Recent methods proposed to aggregate fixed temporal ranges of invisible but anticipated future frames representations as supplementary features and achieved promising performance. They are based on the observation that human beings often detect ongoing actions by contemplating the future vision simultaneously. However, we observed that at different action progressions, the optimal supplementary features should be obtained from distinct temporal ranges instead of simply fixed future temporal ranges. To this end, we introduce an adaptive features sampling strategy to overcome the mentioned variable-ranges of optimal supplementary features. Specifically, in this paper, we propose a novel Learning Action Progression Network termed LAP-Net, which integrates an adaptive features sampling strategy. At each time step, this sampling strategy first estimates current action progression and then decide what temporal ranges should be used to aggregate the optimal supplementary features. We evaluated our LAP-Net on three benchmark datasets, TVSeries, THUMOS-14 and HDD. The extensive experiments demonstrate that with our adaptive feature sampling strategy, the proposed LAP-Net can significantly outperform current state-of-the-art methods with a large margin.