8 citations · 18 across the 20 of their papers we have counts for
27 papers
VerifierBench: Benchmarking the Generation of Executable Verifiers for LLM Agents
Jianing Yin, Ziyi Chen, Hao Wang +4
Agents need reliable ways to validate their outputs, both when completing tasks and when filtering synthetic training data. We study verifier generation: from the instruction and e…
Many Steps into One: Reasoning Contraction and the Limits of Safe Memory Reuse for LLM Agents
Jianghong Zhou, Hao Rong, Chen Lin +1
Thought templates, skill libraries, agent memories and caches turn many reasoning steps into one. We call this reasoning contraction. A contracted memory saves reasoning steps and…
The Imperishable Record, Forgiveness, and the Future of Criminal Justice
Mark Fenwick, Paulius Jurcys, Sebastian Porsdam Mann
Digital technologies can preserve records of wrongdoing indefinitely, and AI can give those records continuing influence over a person's future. We describe this condition as the e…
Words to World: Benchmarking LLMs in Interactive Physical Environments
Xinnan Dai, Kaiqi Yang, Yaxin Li +9
Words are increasingly becoming an interface for action: large language models (LLMs) can now invoke tools, operate devices, and make decisions that affect the physical world. Howe…
Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent
Zheyuan Zhang, Mengyuan Chao, Ke Xiao +5
Modern LLM agents increasingly tackle complex tasks through interactive, long-horizon exchanges with users, while existing benchmarks generally assume that users always accurately…
TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces
Dehai Min, Daoan Zhang, Yiming Zeng +13
An agent can complete a task while exhibiting undesirable behavior during execution. Developers need tests for the specific behaviors encountered in deployment, beyond fixed benchm…
Self-Boosting Vision-Language Models with Noisy Student On-Policy Self-Distillation
Shuai Wang, Daoan Zhang, Zhe Tang +2
Post-training enables vision-language models (VLMs) to understand human instructions and perform various downstream tasks. Current post-training methods usually rely on human-annot…
VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation
Jianhui Wei, Jie Tan, Hengchuan Zhu +7
Agentic long video generation requires planning, tool orchestration, and cross-clip coordination over a long horizon. Most existing video agents either rely on static, human-crafte…
How Far Are Video Models from True Multimodal Reasoning?
Xiaotian Zhang, Jianhui Wei, Yuan Wang +9
Despite remarkable progress toward general-purpose video models, a critical question remains unanswered: how far are these models from achieving true multimodal reasoning? Existing…
Sphinx: Benchmarking and Modeling for LLM-Driven Pull Request Review
Daoan Zhang, Shuo Zhang, Zijian Jin +3
Pull request (PR) review is essential for ensuring software quality, yet automating this task remains challenging due to noisy supervision, limited contextual understanding, and in…
A Versatile Multimodal Agent for Multimedia Content Generation
Daoan Zhang, Wenlin Yao, Xiaoyang Wang +3
With the advancement of AIGC (AI-generated content) technologies, an increasing number of generative models are revolutionizing fields such as video editing, music generation, and…
VisualActBench: Can VLMs See and Act like a Human?
Daoan Zhang, Pai Liu, Xiaofei Zhou +6
Vision-Language Models (VLMs) have achieved impressive progress in perceiving and describing visual environments. However, their ability to proactively reason and act based solely…
JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation
Kai Liu, Jungang Li, Yuchong Sun +13
This paper presents JavisGPT, the first unified multimodal large language model (MLLM) for joint audio-video (JAV) comprehension and generation. JavisGPT has a concise encoder-LLM-…
LAST: LeArning to Think in Space and Time for Generalist Vision-Language Models
Shuai Wang, Daoan Zhang, Tianyi Bai +3
Humans can perceive and understand 3D space and long videos from sequential visual observations. But do vision-language models (VLMs) can? Recent work demonstrates that even state-…
UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist
Zhengyang Liang, Daoan Zhang, Huichi Zhou +8
While specialized AI models excel at isolated video tasks like generation or understanding, real-world applications demand complex, iterative workflows that combine these capabilit…
MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
Guangchen Lan, Sipeng Zhang, Tianle Wang +7
As the era of large language models (LLMs) unfolds, Preference Optimization (PO) methods have become a central approach to aligning LLMs with human preferences and improving perfor…
On Path to Multimodal Generalist: General-Level and General-Bench
Hao Fei, Yuan Zhou, Juncheng Li +29
The Multimodal Large Language Model (MLLM) is currently experiencing rapid growth, driven by the advanced capabilities of LLMs. Unlike earlier specialists, existing MLLMs are evolv…
WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation
Daoan Zhang, Che Jiang, Ruoshi Xu +7
Recent text-to-image (T2I) models achieve high visual fidelity and accurate explicit grounding from input prompts. However, image generation is fundamentally a process of semantic…
Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)
Jing Bi, Susan Liang, Xiaofei Zhou +16
Reasoning is central to human intelligence, enabling structured problem-solving across diverse tasks. Recent advances in large language models (LLMs) have greatly enhanced their re…
Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs
Dayu Yang, Tianyang Liu, Daoan Zhang +8
In large language models (LLMs), code and reasoning reinforce each other: code offers an abstract, modular, and logic-driven structure that supports reasoning, while reasoning tran…
Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization
Daoan Zhang, Guangchen Lan, Dong-Jun Han +8
Existing post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement learning (RL) methods; the former is stable during training but suffer…
DeFine: Decision-Making with Analogical Reasoning over Factor Profiles
Yebowen Hu, Xiaoyang Wang, Wenlin Yao +5
LLMs are ideal for decision-making thanks to their ability to reason over long contexts. However, challenges arise when processing speech transcripts that describe complex scenario…
FINEMATCH: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction
Hang Hua, Jing Shi, Kushal Kafle +5
Recent progress in large-scale pre-training has led to the development of advanced vision-language models (VLMs) with remarkable proficiency in comprehending and generating multimo…
GaussianStyle: Gaussian Head Avatar via StyleGAN
Pinxin Liu, Luchuan Song, Daoan Zhang +5
Existing methods like Neural Radiation Fields (NeRF) and 3D Gaussian Splatting (3DGS) have made significant strides in facial attribute control such as facial animation and compone…