19 citations · 41 across the 27 of their papers we have counts for
29 papers
SkyDrive: Learning to Drive in a New City from Aerial Traffic Monitoring
Weijiang Xiong, Lan Feng, Alexandre Alahi +1
Autonomous driving has made remarkable progress through imitation learning with massive human demonstration data. However, a trained planner often degrades severely when applied to…
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Jinyang Wu, Shuo Yang, Zhengxi Lu +8
Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based rein…
Representation Distribution Matching for One-Step Visual Generation
Lan Feng, Wuyang Li, Eloi Zablocki +2
We elucidate the design space of Representation Distribution Matching (RDM), our name for the paradigm that trains a one-step image generator by matching generated and reference fe…
REAR: Test-time Preference Realignment through Reward Decomposition
Fuxiang Zhang, Pengcheng Wang, Chenran Li +6
Aligning large language models (LLMs) with diverse user preferences is a critical yet challenging task. While post-training methods can adapt models to specific needs, they often r…
OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning
Shuo Yang, Jinyang Wu, Zhengxi Lu +8
Outcome-based reinforcement learning provides a stable optimization backbone for language agents, but its sparse trajectory-level rewards provide little guidance on which intermedi…
EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration
Wuyang Li, Yang Gao, Mariam Hassan +4
We propose EverAnimate, an efficient post-training method for long-horizon animated video generation that preserves visual quality and character identity. Long-form animation remai…
Grounded World Model: Latent Planning with Language Goals
Quanyi Li, Lan Feng, Haonan Zhang +4
World models such as DINO-WM and LeWM specify the goal with an image, which is difficult to obtain in advance for novel tasks. We present the Grounded World Model (GWM), a latent w…
Online Causal Kalman Filtering for Stable and Effective Policy Optimization
Shuo He, Lang Feng, Xin Cheng +2
Reinforcement learning for large language models suffers from high-variance token-level importance sampling (IS) ratios, which would destabilize policy optimization at scale. To im…
Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks
Shuo He, Lang Feng, Qi Wei +3
Group-based reinforcement learning (RL), such as GRPO, has advanced the capabilities of large language models on long-horizon agentic tasks. To enable more fine-grained policy upda…
Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
Lang Feng, Longtao Zheng, Shuo He +2
Multi-agent LLM systems enable advanced reasoning and tool use via role specialization, yet reliable reinforcement learning (RL) post-training for such systems remains difficult. I…
AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection
Junru Zhang, Lang Feng, Haoran Shi +4
Time-series anomaly detection (TSAD) with multimodal large language models (MLLMs) is an emerging area, yet a persistent challenge remains: MLLMs rely on coarse time-series heurist…
AgentOCR: Reimagining Agent History via Optical Self-Compression
Lang Feng, Fuchao Yang, Feng Chen +5
Recent advances in large language models (LLMs) enable agentic systems trained with reinforcement learning (RL) over multi-turn interaction, but practical deployment is bottlenecke…
CaveAgent: Transforming LLMs into Stateful Runtime Operators
Maohao Ran, Zhenglin Wan, Cooper Lin +21
LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms that struggle with long-horizon tasks…
Training Diffusion Policies via Prior-Mapping Co-Evolution
Chubin Zhang, Zhenglin Wan, Feng Chen +7
Reinforcement learning (RL) faces a persistent tension: policies that are stable to optimize (e.g., Gaussians) are often too simple to represent the multimodal action distributions…
RAP: 3D Rasterization Augmented End-to-End Planning
Lan Feng, Yang Gao, Eloi Zablocki +5
Imitation learning for end-to-end driving trains policies only on expert demonstrations. Once deployed in a closed loop, such policies lack recovery data: small mistakes cannot be…
From Stimuli to Minds: Enhancing Psychological Reasoning in LLMs via Bilateral Reinforcement Learning
Yichao Feng, Haoran Luo, Lang Feng +2
Large Language Models show promise in emotion understanding, social reasoning, and empathy, yet they struggle with psychologically grounded tasks that require inferring implicit me…
OmniTraj: Pre-Training on Heterogeneous Data for Adaptive and Zero-Shot Human Trajectory Prediction
Yang Gao, Po-Chien Luan, Kaouther Messaoud +2
While large-scale pre-training has advanced human trajectory prediction, a critical challenge remains: zero-shot transfer to unseen dataset with varying temporal dynamics. State-of…
TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning
Junru Zhang, Lang Feng, Xu Guo +3
Time-series reasoning remains a significant challenge in multimodal large language models (MLLMs) due to the dynamic temporal patterns, ambiguous semantics, and lack of temporal pr…
Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning
Lang Feng, Weihao Tan, Zhiyi Lyu +5
Online fine-tuning vision-language model (VLM) agents with reinforcement learning (RL) has shown promise for equipping agents with multi-step, goal-oriented capabilities in dynamic…
Group-in-Group Policy Optimization for LLM Agent Training
Lang Feng, Zhenghai Xue, Tingcong Liu +1
Recent advances in group-based reinforcement learning (RL) have driven frontier large language models (LLMs) in single-turn tasks like mathematical reasoning. However, their scalab…
Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors
Fan Nie, Lan Feng, Haotian Ye +5
Efficiently leveraging of the capabilities of contemporary large language models (LLMs) is increasingly challenging, particularly when direct fine-tuning is expensive and often imp…
Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning
Zhenghai Xue, Lang Feng, Jiacheng Xu +4
To learn from data collected in diverse dynamics, Imitation from Observation (IfO) methods leverage expert state trajectories based on the premise that recovering expert state dist…
TAROT: Targeted Data Selection via Optimal Transport
Lan Feng, Fan Nie, Yuejiang Liu +1
We propose TAROT, a targeted data selection framework grounded in optimal transport theory. Previous targeted data selection methods primarily rely on influence-based greedy heuris…
UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction
Lan Feng, Mohammadhossein Bahari, Kaouther Messaoud Ben Amor +3
Vehicle trajectory prediction has increasingly relied on data-driven solutions, but their ability to scale to different data domains and the impact of larger dataset sizes on their…