7 papers
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…
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…
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…
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…
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…
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,…