Daily papers of 23 Oct 2026

Daily Papers

Here is the selection of papers for today (23 Oct):

• WeVisOne-VL: Unified Visual Perception from Objects to Pixels (222 ▲)
• Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation (164 ▲)
• Deep Search in Real-World Web Environments (152 ▲)
• Editing Images into Reusable Layers via Compositional Edit-Prior Distillation (73 ▲)
• IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems (54 ▲)
• Toward Recursive Self-Improvement in Physical AI (46 ▲)
• Deep Fusion Memory: A Chunk-Level Parametric Memory for Large Language Models (39 ▲)
• What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models (31 ▲)
• LaLa-World: Scaling Latent World Models with Natural Language Actions (28 ▲)
• Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE (25 ▲)
• Self-Distilling Future Video Representations for World Action Models (23 ▲)
• Policy-Mask: Budget-Aware Adaptation of Diffusion Features to Discriminative Tasks (23 ▲)
• And 37 more papers

NEW - I'm opening Daily Papers! If you're a researcher you can now submit your peers' papers to be featured in Daily Papers directly. Use this page to do so: huggingface.co/papers/submit.

See you soon,
AK and the research community