Tsinghua Researchers Show Diffusion LLMs Reason Better When You Take Away Their Flexibility
Research
Discover latest breakthroughs in Tech
12x Faster Audio Generation Without Discrete Tokens: Kyutai's CALM Framework
Agent Memory Fragmentation Solved: EverMemOS Achieves 93% on LoCoMo via Engram-Inspired Lifecycle
SimpleMem gives LLM agents 30x cheaper memory with 26% better recall
Microsoft's Agent Lightning Decouples RL Training from Agent Logic, Enabling Fine-Tuning of Any AI Agent with Zero Code Changes
18x Faster Audiovisual Generation: Lightricks' Open-Source LTX-2 Rivals Veo 3
Agent Memory Loss Solved: InfiAgent's File-Centric Architecture Enables Unlimited Runtime
4 Percentage Points Better Accuracy With Rude Prompts: How Tone Affects GPT-4o Performance
2.7x Better 3D Reconstruction from Messy Videos: Meta's ShapeR Tackles Real-World Capture
First Cross-Universe Character Mixing: MiMiX Puts Mr. Bean in Tom and Jerry
DeepResearchEval: Benchmark Shows Gemini Leads Quality, Manus Wins Factual Accuracy
40% Faster Video from Single Images: Pixel-to-4D Predicts Dynamic 3D Gaussians in One Pass
6% Better Math Reasoning in Fewer Tokens: Multiplex Thinking Merges Multiple Paths into One
Zero Training Data, Full Performance: Dr. Zero Matches Supervised Search Agents
VLM Hallucinations Exposed: VIB-Probe Pinpoints and Suppresses Faulty Attention Heads
16x Faster On-Device Video Generation: Qualcomm's ReHyAt Distills Attention in 160 GPU Hours
Training-Free Fix Boosts Vision-Language Models 3 Points by Correcting Attention Errors
Gold Medal at IMO and IOI: DeepSeek-V3.2 Matches GPT-5 with Open Weights
Why Reasoning Models Cheat on Efficiency: TNT's Fix Cuts Tokens 50%
Why Chain-of-Thought Works: Researchers Find a Single 'Reasoning Switch' in LLMs
Why Hyper-Connections Explode at Scale: DeepSeek's Manifold Fix
