Daily papers of 2 Nov 2026

Daily Papers

Here is the selection of papers for today (2 Nov):

• FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation (112 ▲)
• R$^2$Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop (89 ▲)
• Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute? (53 ▲)
• REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control (44 ▲)
• Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use (33 ▲)
• Follow the Gradient: Tracing Safety Degradation Back to Training Data (26 ▲)
• WeFair: Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in Short-Video Search (26 ▲)
• Latent Reasoning in Continuous Space for Unified Multimodal Models (25 ▲)
• Wizard: Manipulate Any World in Real Time via Agentic Control (24 ▲)
• HiFOR: Hierarchical Foresight with Action-Guided World Grounding for Vision-Language-Action Model (23 ▲)
• ReLift: Dense 3D Tracking as Lifted Trajectory Repair (22 ▲)
• OSWAM: An Effective World Action Model with One-Step Action Generation (22 ▲)
• And 26 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.

Stay tuned,
AK and the research community