works on

From the 1 of 64 linked papers with an AI index.

activity
20242026
collaborators

64 papers

cs.LG2026

AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses

Cheng Qian, Wenting Zhao, Liangwei Yang +6

Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's parameters, through teacher forcing, on-policy distillation, a…

cs.NE2026

DarwinX: Evolving Agent Harnesses Through Natural Selection

Yifan Zhang, Yutong Dai, Juntao Tan +9

An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control flow. Self-improvement loops already edit harnesses, yet single-…

cs.CV2026

Evidence-Backed Video Question Answering

Shijie Wang, Honglu Zhou, Ziyang Wang +5

The paper introduces Evidence-Backed Video Question Answering (E-VQA), a task where models must provide both a textual answer and precise spatio‑temporal visual evidence (temporal…

cs.DC2026

Mixture-of-Parallelisms: Towards Memory-Efficient Training Stack for Mixture-of-Experts Models

Xuan-Phi Nguyen, Shrey Pandit, Yiran Zhao +3

This paper showcases a memory-efficient training stack for Mixture-of-Experts (MoE) models. It is a training paradigm that combines and specializes various existing and novel paral…

cs.CV2026

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

Ziyang Wang, Honglu Zhou, Shijie Wang +6

Long video understanding (LVU) is challenging because answering real-world queries often depends on sparse, temporally dispersed cues buried in hours of mostly redundant and irrele…

cs.AI2026

BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces

Liangwei Yang, Jielin Qiu, Zixiang Chen +9

Many decision-support settings require systems that adapt to individual users, but evaluation data for this problem remain limited. Existing benchmarks for user understanding often…