- Oct 10, 2026 Causal Pretraining Makes Long Robot Context Pay Off Daily
- Oct 9, 2026 1T Cross-Region Relay-Tree Refit in 150 Seconds at 3% Change Rate Daily
- Oct 8, 2026 Agentic Retrieval Gains 8.7 nDCG@10 Points Over Standard Retrieval With the Same Embedding Model Daily
- Oct 7, 2026 Prism Trains 2.5× Faster and Improves Quality Daily
- Oct 4, 2026 Mean OSWorld Task Score Rises From 33.0% to 40.8% Daily
- Oct 3, 2026 Chunked KV Compression Shows Retrieval Gaps of Up to 40 Percentage Points Daily
- Oct 1, 2026 Across 600 Hard Cases, RSB Searches 50% Fewer Branches Than State-of-the-Art Heuristics Daily
- Sep 29, 2026 Qwen3.5-4B’s Nine-Benchmark Average Retention Reaches 82.3% at 5% Visual Tokens Daily
- Sep 27, 2026 AI Tutoring Matches Expert GRE Learning Gains Daily
- Sep 26, 2026 SpeakerMem Shows Multi-Party Memory Is Still Brittle Daily
- Sep 8, 2026 Teacher Policy Hits 93.57; 3,000 Samples Recover 37.3% Daily
- Sep 6, 2026 Repositories Become Skills as Models Manage Their Own Context Daily
- Sep 5, 2026 Production Traffic, Video Pretraining, and Smarter Distillation Daily
- Sep 2, 2026 Context Shifts Concentrate Occupational Stereotypes Daily
- Sep 1, 2026 Models Detect Impossible Questions but Answer Anyway Daily
- Aug 31, 2026 How Agents Learn to Manage Context and Credit Daily
- Aug 30, 2026 Eleven World Models Miss the Odds; ES Covers More Paths Daily
- Aug 27, 2026 Voice RAG’s F1 Drop Widens by 67% Daily
- Aug 26, 2026 Executable Rubrics Cut Evaluation Latency by Up to 320× Daily
- Aug 15, 2026 Thirteen Skills Push Hallucination Detection to 92% Daily
- Aug 14, 2026 Life Agents, 4D Video, and Sparse Domain Updates Daily
- Aug 10, 2026 Runtime Control Moves Into the Open Daily
- Aug 7, 2026 DAPD Gains Two Points as Diffusion Hits 1,500 Tokens/s Daily
- Aug 4, 2026 CADENA Checks Each Step, MoE Imbalance Exceeds 5× Daily
- Aug 3, 2026 VideoCoCo Pushes VBench to 77.88 Daily
- Jul 26, 2026 Trillion-Parameter MoE Post-Training Runs on Huawei Ascend Daily
- Jul 10, 2026 RL Reaches Image Generation, Gemma 4 Goes Open Daily
- Jul 8, 2026 Avatar Resolution Doubles, Latency Holds at 200ms Daily
- Jul 6, 2026 0.6B Matches 32B, 50x Less VRAM Daily
- Jul 1, 2026 Frontier Agents Finish One Task in Five at 1.6-Hour Length Daily
- Jun 28, 2026 ViQ Speeds Up Multimodal Training 20-70% Daily
- Jun 22, 2026 A Stateful 260M Embedding Beats 8B Specialists Daily
- Jun 19, 2026 Two Loops Take SWE-bench From 43 to 64 Daily
- Jun 18, 2026 Pruning Context Can Cost More Than It Saves Daily
- Jun 17, 2026 A 1.5B Model Beats Sonnet 3.5 at Event Forecasting Daily
- Jun 15, 2026 Pruning a Small Model Is a Shortcut Only on a Tight Budget Daily
- Jun 7, 2026 Streaming Hand-offs Make Multi-Agent Sharper, ZipSplat Splats With 1/6 the Gaussians Daily
- Jun 1, 2026 LoRA as a Ruler for Memory, Reversed Video as a Free Counterfactual Daily
- May 30, 2026 Agents Start Improving Themselves, and Reaching for Fewer Tools Daily
- May 27, 2026 The Rulers We Use to Measure What Models Really Think Are Broken Daily
- May 23, 2026 Optimizer Choice Stretches Capacity Scaling 2.3x Daily
- May 21, 2026 Dual-Stream MoE Unifies Multimodal, Garment Video 30x Faster Daily
- May 20, 2026 Stop When Reasoning Converges, Save 26% of Tokens Daily
- May 14, 2026 Flow-OPD Lifts GenEval From 63 to 92 Daily
- May 8, 2026 T²PO Stabilizes Multi-Turn RL; MotionCache Cuts Video Steps 6x Daily
- May 4, 2026 ViT Pre-Trains Like an LLM, Skips the CLIP Stage Daily
- May 1, 2026 Recursive MAS Cuts Tokens 35%, T2I Repaints Instead of Editing Daily
- Apr 29, 2026 Emotion Probes Crash From 82% to 5% Without Keywords Daily
- Apr 27, 2026 Full Traces Lift Multi-Agent Attribution Accuracy 76% Daily
- Apr 26, 2026 4B Agent on 10K Data, MoE Upcycling Saves 32% Compute Daily
- Apr 22, 2026 Agents Ignore Answers Placed in Plain Sight Daily
- Apr 20, 2026 Open Omni Hits Flagship Scale, Self-Judge Breaks, Reasoning Leaks Forgotten Facts Daily
- Apr 18, 2026 Tencent Open-Sources 3D World Generation, VLM Modal Bias Probe Daily
- Apr 17, 2026 Big Models Resist Rumors but Fall for Noise Daily
- Apr 11, 2026 1.7x Faster From Fine-Tuning Alone, Token Collapse Misdiagnosed Daily
- Apr 9, 2026 120B on One GPU, and 40% of Video Benchmarks Are Guessable Daily
- Apr 4, 2026 Single Neurons Remember Entities, Reusable Routines Boost 19% Daily
- Apr 3, 2026 Minimalist Agents Match MCP, Code Models Think Mid-Stream Daily
- Mar 19, 2026 Open-Source Search Agent Wins With 12K Samples, Agent Skills Mostly Fail Daily
- Mar 18, 2026 700K Paper Pairs Distill Taste, Null Spaces Expose Blind Spots Daily
- Mar 17, 2026 Expert Reasoning Structure for CoT, +13% on Novel Class Discovery Daily
- Mar 16, 2026 Budget-Aware Agents Beat 4x Brute-Force Sampling Daily
- Mar 14, 2026 Encode the Answer, Not the Question — Embeddings Gain 9% Daily
- Mar 12, 2026 Write Code Before You Draw, Layouts Improve 68% Daily
- Mar 11, 2026 4-Step Diffusion Beats 100-Step Baselines, Layer Skipping Saves 18% Daily
- Mar 6, 2026 Code Agents Can't Cross Repo Boundaries, Under 45% Success Daily
- Mar 4, 2026 9K Samples Rival R1, Most RL Gains Trace Back to SFT Daily
- Mar 1, 2026 Latent Reasoning's Gains Aren't From Reasoning Daily
- Feb 25, 2026 Token Probabilities as Zero-Shot Rewards Hit 0.95 Correlation Daily
- Feb 21, 2026 Agents Score Higher but Fail the Same Way Daily
- Feb 20, 2026 Example Pairs Replace Prompts, Agents Play Favorites Daily
- Feb 12, 2026 Text Diffusion Hits Practical Speed, RL Spreads Everywhere Daily
- Feb 10, 2026 LinkedIn Ships LLM-Powered Search Ranking at Scale Daily
- Feb 5, 2026 Kimi K2.5 Open-Sources Agent Swarm, CoT Plans Only 2-3 Steps Ahead Daily
- Feb 4, 2026 Better SFT Makes Worse RL, Distillation Waste, Reward Circuits Daily
- Feb 3, 2026 Zero-Cost Data Mix Search, Guided RLVR, Selective SFT Daily
- Feb 1, 2026 Open-Source Deep Research Beats GPT-5, Embedding Scaling Outshines Experts Daily