Haoyu Zhang
PulseAugur coverage of Haoyu Zhang — every cluster mentioning Haoyu Zhang across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Vision-language models show unreliable refusal behavior tied to image presence
A new research paper from arXiv highlights a significant flaw in vision-language models: their refusal behavior is inconsistently tied to the presence of an image, rather than the content of the request. Researchers fou…
-
New MIRROR framework enhances VLM reasoning by verifying visual grounding
Researchers have introduced MIRROR, a new framework designed to improve the reasoning capabilities of Vision-Language Models (VLMs). MIRROR addresses the issue of hallucinations and logic errors in VLMs by incorporating…
-
New Ex-Omni Model Integrates 3D Facial Animation with LLMs
Researchers have developed Ex-Omni, an open-source model designed to integrate 3D facial animation generation with omni-modal large language models (OLLMs). This model addresses the challenge of bridging LLMs' discrete …