Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling Paper • 2605.13301 • Published May 13 • 165
Representation Forcing for Bottleneck-Free Unified Multimodal Models Paper • 2605.31604 • Published about 1 month ago • 63
LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards Paper • 2605.31584 • Published about 1 month ago • 43
GrepSeek: Training Search Agents for Direct Corpus Interaction Paper • 2605.29307 • Published May 28 • 115
GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration Paper • 2605.31039 • Published about 1 month ago • 46
Parallelized Hierarchical Connectome: A Spatiotemporal Recurrent Framework for Spiking State-Space Models Paper • 2604.01295 • Published May 20 • 1
Scalable Learning in Structured Recurrent Spiking Neural Networks without Backpropagation Paper • 2605.00402 • Published May 1 • 1
Rethinking Cross-Layer Information Routing in Diffusion Transformers Paper • 2605.20708 • Published May 20 • 111
From Pixels to Words -- Towards Native One-Vision Models at Scale Paper • 2605.28820 • Published May 27 • 75
GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling Paper • 2604.18556 • Published Apr 20 • 9
Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration Paper • 2605.05566 • Published May 7 • 38
Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning Paper • 2602.06600 • Published Feb 6 • 3
PowerInfer-2: Fast Large Language Model Inference on a Smartphone Paper • 2406.06282 • Published Jun 10, 2024 • 40
ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Paper • 2605.00380 • Published May 1 • 7
EMO: Pretraining Mixture of Experts for Emergent Modularity Paper • 2605.06663 • Published May 7 • 12
Evaluating the Progression of Large Language Model Capabilities for Small-Molecule Drug Design Paper • 2604.16279 • Published Apr 17 • 1
view article Article CyberSecQwen-4B: Why Defensive Cyber Needs Small, Specialized, Locally-Runnable Models lablab-ai-amd-developer-hackathon • May 8 • 10