Category: Large Language Models

• Demystifying the Sparse LLM Innovation by NVIDIA and Sakana AI
• The True Capabilities of LLMs Exposed: 90% in Python, 0% in Whitespace! The 'Top Student' Persona of AI Crumbles
• 500 Seed Samples, Four Self-Evolving Agents: Reasoning Capability Surges by 10.7%
• SortedRL: Accelerates Large Model RL Training by 50%, Boosting Efficiency by 18%
• Top Models Like GPT-5.4 and Claude Opus Exposed for 'Fake Reasoning': Is the Problem-Solving Process Just a 'Performance'?
• Inference No Longer Wastes Cycles on Logits: FlashSampling Accelerates Decoding by 19%
• Can LLMs Be Computers?
• Injecting Continuous New Knowledge into Large Models: Beihang's CASE Framework Edits Thousands of Times Without Forgetting, Adding Less Than 1MB of Parameters | WWW'26
• Lin Junyang Speaks Out for the First Time After Leaving Alibaba: Reviewing Qwen's Detours, Pointing to AI's New Path
• VideoSeek Long-Video Understanding Agent: The Secret to Boosting GPT-5's Long-Video Comprehension by 10 Points
• Let AI 'Refine' Its Own Data! DataChef Goes Open Source: Using Reinforcement Learning to Automatically Generate LLM Data Recipes
• The AI Grad Student Who Can Do Theoretical Physics Is Here—Is There No Going Back? A Harvard Professor's Insights You Must Read
• TurboQuant: Redefining AI efficiency with extreme compression
• NVIDIA Nemotron-Cascade 2 Technical Report
• ICLR 2026 | How Far Can Unsupervised Reinforcement Learning Go for Large Models? A Systematic Answer from the Tsinghua Team
• Stop Obsessing Over Outcome Rewards! CUHK Identifies and Solves the "Information Self-Locking" Problem in RL!
• One Year into RAG: My Biggest Regret Was Adopting Knowledge Graphs
• Karpathy Just Open-Sourced AutoResearch: I Used It to Optimize Lobster Skills, Boosting Success Rates from 56% to 92%
• The Age of Agent Skills: How Big is the Gap Between Strong and Weak Models? Shattering the 'Cheap Alternative' Illusion | Latest from Oxford
• OpenAI's New Model Rejected on Day 0! Ranks Poorly, Lagging Behind Domestic Models Released in Late January
• 4B Model Surpasses GPT-5 in Hallucination Suppression: CMU and Others Propose New Behaviorally Calibrated Reinforcement Learning Method
• Masterpiece! MIT and Google Train an LLM Capable of Rigorous Bayesian Inference
• Breaking Static Model Weights! Tencent Hunyuan Releases Real-Time Brain-Switching Technology for Inference
• MMLU is Dead? 'Humanity's Last Exam' Published in Nature: Global AI Models Collectively Fail!
• Why Can Large Language Models 'Understand' the World?