Jong Chul Ye
PulseAugur coverage of Jong Chul Ye — every cluster mentioning Jong Chul Ye across labs, papers, and developer communities, ranked by signal.
-
New CRePE method enhances camera control in video generation models
Researchers have developed a new method called Curved Ray Expectation Positional Encoding (CRePE) to improve video generation models. CRePE addresses limitations in existing camera encoding techniques by representing im…
-
FILT3R layer enhances streaming 3D reconstruction with adaptive Kalman filter
Researchers have introduced FILT3R, a novel training-free layer designed to improve streaming 3D reconstruction by adaptively updating latent states. This method treats state updates as stochastic estimations in token s…
-
Memory-V2V framework enhances multi-turn video editing consistency
Researchers have developed Memory-V2V, a novel framework designed to improve consistency in multi-turn video editing. Existing video-to-video diffusion models often struggle with sequential edits, leading to inconsisten…
-
InverseCrafter framework enables efficient video re-capture without VDM fine-tuning
Researchers have introduced InverseCrafter, a novel framework for generating novel views of videos without requiring extensive fine-tuning of pre-trained Video Diffusion Models (VDMs). This approach treats video re-capt…
-
AgentPSO framework evolves LLM reasoning skills using particle swarm optimization
Researchers have developed AgentPSO, a novel framework that uses a particle swarm optimization approach to enhance the reasoning capabilities of large language models. Unlike existing methods that rely on inference-time…
-
New PACE-RAG framework enhances personalized drug recommendations for Parkinson's patients
Researchers have developed PACE-RAG, a novel retrieval-augmented generation framework designed to improve drug recommendations for patients with complex conditions like Parkinson's disease. Unlike existing methods that …