activity
20242026
collaborators
Showing cs.CLShow all

15 papers · 1 filter

cs.CL2026

Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies

Ming Liu

Successive self-training on a language model's own outputs is widely characterized as a process of flattening: diversity drops, distributions narrow, and the text becomes "more lik…

cs.CL2026

Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs

Jiafeng Liang, Zhihao Zhu, Zihan Zhang +7

Although Large Multimodal Models (LMMs) have achieved strong performance on general video understanding, their susceptibility to textual prior shortcuts during causal discovery has…

cs.CL2026

LoopRPT: Reinforcement Pre-Training for Looped Language Models

Guo Tang, Shixin Jiang, Heng Chang +6

Looped language models (LoopLMs) perform iterative latent computation to refine internal representations, offering a promising alternative to explicit chain-of-thought (CoT) reason…

cs.CL2026

Scalable Multilingual Multimodal Machine Translation with Speech-Text Fusion

Yexing Du, Youcheng Pan, Zekun Wang +7

Multimodal Large Language Models (MLLMs) have achieved notable success in enhancing translation performance by integrating multimodal information. However, existing research primar…

cs.CL2025

AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents

Jiafeng Liang, Hao Li, Chang Li +12

Memory serves as the pivotal nexus bridging past and future, providing both humans and AI systems with invaluable concepts and experience to navigate complex tasks. Recent research…

cs.CL2025

EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models

Zekun Wang, Minghua Ma, Zexin Wang +4

Large Vision-Language Models (LVLMs) have achieved remarkable success, yet their significant computational demands hinder practical deployment. While efforts to improve LVLM effici…