paper / vinod-khosla / May 19 / failedFine-tuning Pocket-Aware Diffusion Models via Denoising Policy Optimization
paper / vinod-khosla / May 8 / failedStress Tests REVEAL Fragile Temporal and Visual Grounding in Video-Language Models
paper / vinod-khosla / May 8 / failedPartial Soft-Matching Distance for Neural Representational Comparison with Partial Unit Correspondence
paper / vinod-khosla / May 8 / failedMeasuring the Representational Alignment of Neural Systems in Superposition
paper / vinod-khosla / May 8 / failedGeometry-Aware CLIP Retrieval via Local Cross-Modal Alignment and Steering
paper / vinod-khosla / May 8 / failedT-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalability