Keyur

Tensor Manipulation Unit (TMU)

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights

AbsenceBench: Language Models Can't Tell What's Missing

Spherical CNNs

Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence

Scaling Test time Compute for LLM Agents

Gemini 2 5 Technical Report

MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

Aligned Novel View Image and Geometry Synthesis via Cross modal Attention Instillation

The Diffusion Duality

Magistral

Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models

ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning

JavelinGuard: Low-Cost Transformer Architectures for LLM Security

Reinforcement Pre-Training

Will It Still Be True Tomorrow?

Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

Log-Linear Attention

VS-Bench: Evaluating VLMs for Strategic Reasoning and Decision-Making in Multi-Agent Environments

Test-Time Training Done Right

Taming LLMs by Scaling Learning Rates with Gradient Grouping

Beyond the 80/20 Rule

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

The Resurrection of the ReLU

Table-R1: Inference-Time Scaling for Table Reasoning

ZeroGUI: Automating Online GUI Learning at Zero Human Cost

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs

AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation