activity
20242026
collaborators

15 papers

cs.CV2026

BabyVision: Visual Reasoning Beyond Language

Liang Chen, Weichu Xie, Yiyan Liang +27

While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile…

cs.CV2026

Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance

Haozhe Zhao, Shuzheng Si, Liang Chen +4

Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. However, despite showing promising performance, LVLMs suffer from hallucinat…

cs.AI2026

SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?

Kean Shi, Zihang Li, Tianyi Ma +13

Computer-Using Agents (CUAs) are rapidly extending large language models (LLMs) beyond text-based reasoning toward action execution in more complex environments, such as web browse…

cs.SE2026

RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades

Xinbo Xu, Ruihan Yang, Haiyang Shen +13

Coding agents are increasingly deployed in real software development, where a single version iteration requires months of coordinated work across many files. However, most existing…

cs.LG2026

Improving MLLM Training Efficiency via Stage-Aware Sparsity

Kean Shi, Liang Chen, Haozhe Zhao +1

Multimodal Large Language Models (MLLMs) have demonstrated outstanding performance across a variety of domains. However, training MLLMs is often inefficient, as much of the computa…

cs.CL2026

LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards

Bowen Ping, Zijun Chen, Yiyao Yu +3

Reinforcement Learning has emerged as a key driver for LLM reasoning. This capability is equally pivotal in long-context scenarios--such as long-dialogue understanding and structur…