works on

From the 1 of 192 linked papers with an AI index.

activity
20242026
most citedIt's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents

1 citations · 2 across the 25 of their papers we have counts for

collaborators

192 papers

cs.CV2026

Self-Supervised Visual On-Policy Distillation

Yijiang Li, Yijun Liang, Yunjie Tian +6

Visual on-policy distillation relies heavily on an informative teacher-student asymmetry, through either a larger, stronger teacher or privileged supervision, such as reference ans…

cs.CV2026

Multimodal Model Diffing for Feature Discovery and Control

Hunar Batra, Lachin Naghashyar, Ashkan Khakzar +4

Multimodal Large Language Models (MLLMs) exhibit strong visual understanding, yet the internal features that cause these behaviors remain difficult to identify, audit, or control.…

cs.AI2026

LatticeMind: A Conflict-Aware Memory Primitive for Multi-Agent Systems

Heng Zhou, Lian Zhang, Yutao Fan +5

Multi-agent LLM systems often fail not for lack of candidate answers, but because they have no persistent mechanism for deciding which incompatible claim should currently be truste…

cs.CV2026

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

Junlin Han, Shengbang Tong, David Fan +4

Vision offers a critical axis for advancing foundation models, driving a shift towards natively unified multimodal pretraining. Despite this momentum, the design space and the fund…

cs.AI2026

MatrAIx: Simulating the World with 8.3 Billion Persona Agents

Xiaomin Li, Yuexing Hao, Jianheng Hou +90

Human evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but often abstract away human diversity and inter…

cs.AI2026

Learning Clinical-Trial Strategy: Offline Policy Training for Decision Agents

William Bolton, Philip Torr

Clinical development is sequential decision-making under uncertainty, where a sponsor must plan a portfolio of experiments from heterogeneous evidence. We study this setting by fra…