The Decode-Work Law: Margin-Governed, Provably-Exact Spatial Joins over Compressed Geometry

Neural Certificate Pricing for Combinatorial Optimization Problems

Optimal Resource Utilization for Autonomous Laboratory Orchestrators

TERA: A Unified Taylor Model Enabled Reachability Analysis Framework

Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning

Trie-based Experiment Plans for Efficient IR Pipeline Experiments

On the Nonlinearity of Learning Rate Scaling for LLM Training

Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views

BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding

DOPD: Dual On-policy Distillation

Dockerless: Environment-Free Program Verifier for Coding Agents

Orca: The World is in Your Mind

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Finding the Time to Think: Learning Planning Budgets in Real-Time RL

What do near-optimal learning rate schedules look like?

Beyond IID: How General Are Tabular Foundation Models, Really?

ReFreeKV: Towards Threshold-Free KV Cache Compression

TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents

SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning

Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs

MultiHashFormer: Hash-based Generative Language Models

Qwen-Image-2.0-RL Technical Report

Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots

PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation

OpenTME: An Open Dataset of AI-powered H&E Tumor Microenvironment Profiles from TCGA

FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling

The Decode-Work Law: Margin-Governed, Provably-Exact Spatial Joins over Compressed Geometry

Neural Certificate Pricing for Combinatorial Optimization Problems

Optimal Resource Utilization for Autonomous Laboratory Orchestrators

TERA: A Unified Taylor Model Enabled Reachability Analysis Framework

Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning

Trie-based Experiment Plans for Efficient IR Pipeline Experiments

On the Nonlinearity of Learning Rate Scaling for LLM Training

Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views

BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding

DOPD: Dual On-policy Distillation

Dockerless: Environment-Free Program Verifier for Coding Agents

Orca: The World is in Your Mind

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Finding the Time to Think: Learning Planning Budgets in Real-Time RL

What do near-optimal learning rate schedules look like?

Beyond IID: How General Are Tabular Foundation Models, Really?

ReFreeKV: Towards Threshold-Free KV Cache Compression

TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents

SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning

Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs

MultiHashFormer: Hash-based Generative Language Models

Qwen-Image-2.0-RL Technical Report

Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots

PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation

OpenTME: An Open Dataset of AI-powered H&E Tumor Microenvironment Profiles from TCGA

FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling