Daily papers of 30 Oct 2026

Daily Papers

Here is the selection of papers for today (30 Oct):

• Intrinsic Distribution Matching (238 ▲)
• A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement (150 ▲)
• Your Benchmark Is an Empirical Measure Over Difficulty (140 ▲)
• Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs (91 ▲)
• Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities (55 ▲)
• Proving and Improving the Platonic Representation Hypothesis with JEPAs (53 ▲)
• L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory (34 ▲)
• WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training (30 ▲)
• A Broader Look into MLLM's Retrieval Heads (28 ▲)
• Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers (26 ▲)
• Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models (19 ▲)
• VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team (18 ▲)
• And 27 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.

Until next time,
AK and the research community