works on

From the 4 of 35 linked papers with an AI index.

collaborators

35 papers

cs.CV2026

Do Unified Multimodal Models Think in One Space? A Lens Through Cross-Branch Steering

Yu Wang, Sharon Li

The paper investigates whether unified multimodal models share a common semantic space by introducing cross-branch semantic steering, showing that semantic directions from the unde…

cs.LG2026

TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents

Leitian Tao, Baolin Peng, Wenlin Yao +5

The paper proposes TRACE, a turn-level reward assignment method that estimates credit for each tool-call in long-horizon agents using log‑ratio state values and temporal‑difference…

cs.AI2026

Tracing Agentic Failure from the Flow of Success

Samuel Yeh, Yiwen Zhu, Shaleen Deep +1

The paper introduces OAT, a lightweight unsupervised method that learns from successful LLM agent trajectories and detects error steps in failed runs by scoring deviations using ne…

cs.MA2026

Multi-Agent LLMs Fail to Explore Each Other

Hyeong Kyu Choi, Jiatong Li, Wendi Li +2

The paper shows that large language model agents struggle to explore each other in multi-agent settings, leading to poor coordination, and introduces the MACE framework that uses s…

cs.LG2026

VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild

Junlin Fang, Wenyu Chen, Reshmi Ghosh +7

Vision-language Models (VLMs) are essential for contextual understanding of both visual and textual information. However, their vulnerability to adversarially manipulated inputs pr…

cs.LG2026

Multi-Head Recurrent Memory Agents

Jiatong Li, Samuel Yeh, Sharon Li

Recurrent memory agents extend LLMs to arbitrarily long contexts by iteratively consolidating input into a fixed-size memory window. Despite their scalability, these agents exhibit…