2 citations · 3 across the 16 of their papers we have counts for
18 papers
ResOPD: Tail Residualization for Sparse On-Policy Distillation
Penghui Yang, Long Xing, Xuanlang Dai +3
On-policy distillation (OPD) trains a student model on self-generated trajectories, but transmitting dense teacher distributions across long reasoning traces creates prohibitive co…
Rollout Cards: A Reproducibility Standard for Agent Research
Charlie Masters, Ziyuan Liu, Stefano V. Albrecht
Reproducibility problems that have long affected machine learning and reinforcement learning are now surfacing in agent research: papers compare systems by reported scores while le…
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
Shuangrui Ding, Xuanlang Dai, Long Xing +14
Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still…
Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning
Songyuan Yang, Weijiang Yu, Jilin Ma +5
Video reasoning has advanced with large multimodal models (LMMs), yet their inference is often a single pass that returns an answer without verifying whether the reasoning is evide…
Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning
Songyuan Yang, Weijiang Yu, Ziyu Liu +4
When video reasoning requires external knowledge, many systems with large multimodal models (LMMs) adopt retrieval augmentation to supply the missing context. Appending textual or…
Visual-ERM: Reward Modeling for Visual Equivalence
Ziyu Liu, Shengyuan Ding, Xinyu Fang +7
Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured representations with high visual fideli…
ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning
Shengyuan Ding, Xinyu Fang, Ziyu Liu +10
Reward models are critical for aligning vision-language systems with human preferences, yet current approaches suffer from hallucination, weak visual grounding, and an inability to…
SPARK: Synergistic Policy And Reward Co-Evolving Framework
Ziyu Liu, Yuhang Zang, Shengyuan Ding +5
Recent Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) increasingly use Reinforcement Learning (RL) for post-pretraining, such as RL with Verifiable Rewards (…
CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning
Zeyi Sun, Yuhang Cao, Jianze Liang +8
Autonomous agents for Graphical User Interfaces (GUIs) face significant challenges in specialized domains such as scientific computing, where both long-horizon planning and precise…
SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience
Zeyi Sun, Ziyu Liu, Yuhang Zang +5
Repurposing large vision-language models (LVLMs) as computer use agents (CUAs) has led to substantial breakthroughs, primarily driven by human-labeled data. However, these models o…
Visual Agentic Reinforcement Fine-Tuning
Ziyu Liu, Yuhang Zang, Yushan Zou +6
A key trend in Large Reasoning Models (e.g., OpenAI's o3) is the native agentic ability to use external tools such as web browsers for searching and writing/executing code for imag…
Visual-RFT: Visual Reinforcement Fine-Tuning
Ziyu Liu, Zeyi Sun, Yuhang Zang +5
Reinforcement Fine-Tuning (RFT) in Large Reasoning Models like OpenAI o1 learns from feedback on its answers, which is especially useful in applications when fine-tuning data is sc…
InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model
Yuhang Zang, Xiaoyi Dong, Pan Zhang +10
Despite the promising performance of Large Vision Language Models (LVLMs) in visual understanding, they occasionally generate incorrect outputs. While reward models (RMs) with rein…
MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models
Ziyu Liu, Yuhang Zang, Xiaoyi Dong +7
Visual preference alignment involves training Large Vision-Language Models (LVLMs) to predict human preferences between visual inputs. This is typically achieved by using labeled d…
MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations
Yubo Ma, Yuhang Zang, Liangyu Chen +13
Understanding documents with rich layouts and multi-modal components is a long-standing and practical task. Recent Large Vision-Language Models (LVLMs) have made remarkable strides…
V3Det Challenge 2024 on Vast Vocabulary and Open Vocabulary Object Detection: Methods and Results
Jiaqi Wang, Yuhang Zang, Pan Zhang +31
Detecting objects in real-world scenes is a complex task due to various challenges, including the vast range of object categories, and potential encounters with previously unknown…
MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs
Ziyu Liu, Tao Chu, Yuhang Zang +8
Generating natural and meaningful responses to communicate with multi-modal human inputs is a fundamental capability of Large Vision-Language Models(LVLMs). While current open-sour…
RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition
Ziyu Liu, Zeyi Sun, Yuhang Zang +6
CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of candidates, yet its focus on broad asso…