【本日の論文】
1. NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
https://huggingface.co/papers/2609.08183
2. AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing
https://huggingface.co/papers/2609.08936
3. Omni Interaction Agent Technical Report
https://huggingface.co/papers/2609.08977
4. Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation
https://huggingface.co/papers/2609.08798
5. DriveZero: End-to-End Driving Beyond Human Demonstrations
https://huggingface.co/papers/2609.06055

【本日の論文】
1. Unlocking Lossless Speedups in LLMs via Discrete Diffusion
https://huggingface.co/papers/2609.04010
2. FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience
https://huggingface.co/papers/2609.03241
3. ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation
https://huggingface.co/papers/2609.03756
4. Causal Foundation Models
https://huggingface.co/papers/2609.03003
5. Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation
https://huggingface.co/papers/2609.02998

【本日の論文】
1. Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems
https://huggingface.co/papers/2609.02750
2. Iris: Climbing to the Search Frontier
https://huggingface.co/papers/2609.04304
3. Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue
https://huggingface.co/papers/2609.04250
4. The Attention Triangle in Audio-Video Models
https://huggingface.co/papers/2609.03586
5. WorldSculpt: Generating Compositional Worlds from Grounded Videos
https://huggingface.co/papers/2609.05416

【本日の論文】
1. Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
https://huggingface.co/papers/2609.04199
2. Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
https://huggingface.co/papers/2609.04148
3. LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes
https://huggingface.co/papers/2609.03796
4. Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
https://huggingface.co/papers/2609.03430
5. Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
https://huggingface.co/papers/2608.26730

【本日の論文】
1. Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
https://huggingface.co/papers/2609.04199
2. Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
https://huggingface.co/papers/2609.04148
3. LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes
https://huggingface.co/papers/2609.03796
4. Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
https://huggingface.co/papers/2609.03430
5. Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
https://huggingface.co/papers/2608.26730

【本日の論文】
1. Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
https://huggingface.co/papers/2609.04199
2. Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
https://huggingface.co/papers/2609.04148
3. LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes
https://huggingface.co/papers/2609.03796
4. Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
https://huggingface.co/papers/2608.26730
5. Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
https://huggingface.co/papers/2609.03430

【本日の論文】
1. Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
https://huggingface.co/papers/2609.02749
2. HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
https://huggingface.co/papers/2609.01437
3. Aspire: Can Models Self-Evolve from Vague Goals?
https://huggingface.co/papers/2608.31111
4. SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
https://huggingface.co/papers/2609.02886
5. EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction
https://huggingface.co/papers/2609.02783

【本日の論文】
1. StudentSim: Training LLM-based Student Simulators
https://huggingface.co/papers/2609.01591
2. Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
https://huggingface.co/papers/2609.00111
3. SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers
https://huggingface.co/papers/2609.01343
4. UI-Venus-2 Technical Report
https://huggingface.co/papers/2609.00028
5. H3-World: Turning Language Understanding into World Control
https://huggingface.co/papers/2609.01560

【本日の論文】
1. Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement
https://huggingface.co/papers/2608.31046
2. DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution
https://huggingface.co/papers/2608.31106
3. Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling
https://huggingface.co/papers/2608.30821
4. GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling
https://huggingface.co/papers/2608.29335
5. Normalized Low-Rank Adaptation
https://huggingface.co/papers/2608.31036

【本日の論文】
1. LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering
https://huggingface.co/papers/2608.28281
2. Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models
https://huggingface.co/papers/2608.27550
3. DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents
https://huggingface.co/papers/2608.18524
4. Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities
https://huggingface.co/papers/2608.28122
5. Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning
https://huggingface.co/papers/2608.27549