6 papers
WinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding
Chenxu Wang, Hangyi Kuang, Bo-Wen Yin +6
MLLM-based detectors formulate vision-language grounding as autoregressive coordinate generation, yet in dense scenes, they often collapse into a box repetition loop, repeatedly em…
Massive Activation Gating Channel in Large Language Models
Minjia Mao, Shi Chen, Bowen Yin +1
Massive activations, a phenomenon in which a small number of hidden channels exhibit exceptionally large magnitudes, are pervasive in large language models (LLMs). However, the mec…
See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding
Boyuan Sun, Bowen Yin, Yuanming Li +2
We present SWIM (See What I Mean), a novel training strategy that aligns vision and language representations to enable fine-grained object understanding solely from textual prompts…
Early Stopping Chain-of-thoughts in Large Language Models
Minjia Mao, Bowen Yin, Yu Zhu +1
Reasoning large language models (LLMs) have demonstrated superior capacities in solving complicated problems by generating long chain-of-thoughts (CoT), but such a lengthy CoT incu…
Depth Anything at Any Condition
Boyuan Sun, Modi Jin, Bowen Yin +1
We present Depth Anything at Any Condition (DepthAnything-AC), a foundation monocular depth estimation (MDE) model capable of handling diverse environmental conditions. Previous fo…
HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context
Qize Yang, Shimin Yao, Weixuan Chen +7
With the rapid evolution of multimodal large language models, the capacity to deeply understand and interpret human intentions has emerged as a critical capability, which demands d…