works on

From the 1 of 7 linked papers with an AI index.

collaborators

7 papers

cs.CV2026

PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models

Zichao Lin, Yifeng Xie, Bowen Qu +30

We introduce PerceptionBench, a benchmark specifically designed to evaluate the atomic visual perception capabilities of Multimodal Large Language Models (MLLMs). Existing benchmar…

cs.CL2026

Kimi K3: Open Frontier Intelligence

Kimi Team, Tongtong Bai, Yifan Bai +398

We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is…

cs.AI2026

Demonstrating TOFFEE: A Learned System for Synthesizing Data Agent Trajectories at Scale

Ziting Wang, Yin Li, Zuhao Yang +3

The paper presents TOFFEE, a system that uses Monte Carlo Tree Search and learned cost models to automatically generate data‑agent interaction trajectories for diverse data environ…

cs.CV2026

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

Zuhao Yang, Sudong Wang, Kaichen Zhang +8

Large multimodal models (LMMs) have shown great potential for video reasoning with textual Chain-of-Thought. However, they remain vulnerable to hallucinations, especially when proc…

cs.CV2026

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors

Keming Wu, Yijing Cui, Wenhan Xue +11

Commercial video generation systems such as Seedance2.0 and Veo3.1 have rapidly improved, strengthening the view that video generators may be evolving into "world simulators." Yet…

cs.CV2026

SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration

Zhongyu Yang, Zuhao Yang, Shuo Zhan +3

Video question answering (VideoQA) is a challenging task that requires integrating spatial, temporal, and semantic information to capture the complex dynamics of video sequences. A…