collaborators

7 papers

cs.CL2026

Hidden Decoding at Scale: Latent Computation Scaling for Large Language Models

Aiwei Liu, Cheng Shi, Chuhan Wu +44

Scaling Large Language Models (LLMs) has been driven mainly by enlarging the Transformer backbone, but for an already-strong model this requires another round of costly pretraining…

cs.CV2026

Vision Transformers Need More Than Registers

Cheng Shi, Yizhou Yu, Sibei Yang

Vision Transformers (ViTs), when pre-trained on large-scale data, provide general-purpose representations for diverse downstream tasks. However, artifacts in ViTs are widely observ…

cs.CV2026

WeaveTime: Stream from Earlier Frames into Emergent Memory in VideoLLMs

Yulin Zhang, Cheng Shi, Sibei Yang

Recent advances in Multimodal Large Language Models have greatly improved visual understanding and reasoning, yet their quadratic attention and offline training protocols make them…

cs.CV2025

Sim-DETR: Unlock DETR for Temporal Sentence Grounding

Jiajin Tang, Zhengxuan Wei, Yuchen Zhu +4

Temporal sentence grounding aims to identify exact moments in a video that correspond to a given textual query, typically addressed with detection transformer (DETR) solutions. How…

cs.CV2025

Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video

Yulin Zhang, Cheng Shi, Yang Wang +1

Envision an AI capable of functioning in human-like settings, moving beyond mere observation to actively understand, anticipate, and proactively respond to unfolding events. Toward…

cs.CV2025

Vision Function Layer in Multimodal LLMs

Cheng Shi, Yizhou Yu, Sibei Yang

This study identifies that visual-related functional decoding is distributed across different decoder layers in Multimodal Large Language Models (MLLMs). Typically, each function,…