AI Native Daily Paper Digest – 20260410
1. Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability 🔑 Keywords: supervised finetuning, reinforcement…
AI Native Daily Paper Digest – 20260409
1. Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning 🔑 Keywords: Process-driven image generation, Multimodal models, Textual…
AI Native Daily Paper Digest – 20260408
1. Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding 🔑 Keywords: Video Understanding, Robustness, Faithfulness, Video-MME-v2, Multimodal…
AI Native Daily Paper Digest – 20260406
1. Self-Distilled RLVR 🔑 Keywords: Reinforcement Learning, Verifiable Rewards, Self-distillation, Training Stability, On-policy Distillation 💡 Category: Reinforcement Learning 🌟 Research…
AI Native Daily Paper Digest – 20260403
1. DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models 🔑 Keywords: Data-centric training, Large language models,…
AI Native Daily Paper Digest – 20260401
1. FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization 🔑 Keywords: FIPO, Reinforcement Learning, Discounted Future-KL Divergence, Dense Advantage…
AI Native Daily Paper Digest – 20260331
1. TAPS: Task Aware Proposal Distributions for Speculative Sampling 🔑 Keywords: Speculative decoding, draft model, confidence-based routing, acceptance length 💡…
AI Native Daily Paper Digest – 20260330
1. Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models 🔑 Keywords: Hybrid Memory,…
AI Native Daily Paper Digest – 20260327
1. PixelSmile: Toward Fine-Grained Facial Expression Editing 🔑 Keywords: PixelSmile, facial expression editing, semantic overlap, diffusion framework, contrastive learning 💡…