1 citations · 1 across the 9 of their papers we have counts for
11 papers · 1 filter
Dual Exam: Controlled Evaluation of Multimodal Agents and World Models
Zhefan Rao, Meng Chu, Xuan Zhang +80
World Models (WMs) can support Multimodal Agents (MAs) through simulated experience, while Agent trajectories can inform World Model refinement. Evaluating this interaction require…
Coopshift: Post-Training Amplifies The Memory Curse In LLM Cooperation
Jiayuan Liu, Shiyi Du, Tianqin Li +3
How does post-training change cooperation during repeated interaction? Within each of seven released model lineages, we compare pretrained (Base), supervised fine-tuned (SFT), and…
Learning When to Think: Utility-Guided Adaptive Reasoning for Efficient Text Retrieval
Yingtao Luo, Kangyi Zhao, Shiyi Du +1
Reasoning-conditioned embeddings can improve retrieval by progressively refining semantic constraints. However, additional reasoning may introduce over-generalized or semantically…
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
Fang Wu, Da Xing, Yanjie Huang +16
Modern multimodal models bring generation and understanding into a single unified system, which enables them to provide and learn from their own feedback. Motivated by this unified…
UXBench: Measuring the Actionability of LLM-Generated UX Critiques
Wenjie Wang, Yue Huang, Zipeng Ling +11
Large language models (LLMs) are increasingly deployed as UX judges that inspect interfaces, diagnose usability problems, and propose repairs. Yet no controlled benchmark measures…
Reward Transport: Property Control in Flow Matching via Noise-Space Alignment
Kehan Guo, Yili Shen, Yujun Zhou +4
The coupling in flow matching -- the rule pairing noise vectors with data points -- is typically treated as a computational choice. We show that this coupling can instead serve as…
SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic Data
Wenjie Wang, Yue Huang, Zhengqing Yuan +6
As large language models (LLMs) are increasingly deployed in real-world applications, alignment is no longer governed by a single universal notion of safety or helpfulness, but ins…
The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents
Jiayuan Liu, Tianqin Li, Shiyi Du +7
Context window expansion is often treated as a straightforward capability upgrade for LLMs, but we find it systematically fails in multi-agent social dilemmas. Across 7 LLMs and 4…
Why Search When You Can Transfer? Amortized Agentic Workflow Design from Structural Priors
Shiyi Du, Jiayuan Liu, Weihua Du +6
Automated agentic workflow design currently relies on per-task iterative search, which is computationally prohibitive and fails to reuse structural knowledge across tasks. We obser…
The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration
Jiayuan Liu, Shiyi Du, Weihua Du +2
Multi-agent large language model (LLM) architectures increasingly rely on response-level aggregation, such as Majority Voting (MAJ), to raise reasoning ceilings. However, in open e…
Models Know Their Shortcuts: Deployment-Time Shortcut Mitigation
Jiayi Li, Shijie Tang, Gün Kaynar +2
Pretrained text encoders are prone to shortcut learning, relying on token-label correlations that fail once the distribution shifts in deployment. Existing shortcut mitigation meth…