Fields

REKI: Registering Knowledge in VLAs

MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering

Data Strategies for Large Language Models: A Unified Perspective on the Training Lifecycle

When the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel Prefill

KnowGPO: Knowledge-Grouped Policy Optimization for Search Agents

MedPAO-VL: Interpretable and Protocol-Compliant Agent for Structured Radiology Report Generation

Your Transformer Is Secretly Elastic

Gen4P: Video Generators are 4D Perceivers

Realtime-Bench: Can Frontier Models Solve Real-time Interactive Problems?

Realtime-Bench: Can Frontier Models Solve Real-time Interactive Problems?

Are You Sure Your LLM Is Sure? Repairing and Auditing Confidence

On the Stability and Convergence of Flow Map Training

PathFM: Fast Generative Forecasting of Multivariate Trajectories

MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering

Training-Free On-Policy Distillation

Gen4P: Video Generators are 4D Perceivers

When Reasoning Is Not Enough: Proactive Inquiry for Cross-Modal Safety in Multimodal Large Language Models

Generalization Guarantees of Randomized Block Coordinate Descent for Nonconvex Learning

MolLean: A Process-Verifiable Language for Chemical Reasoning

Private Retrieval Augmented Generation via Random Projection

FeaTok: Feature-Loss Tokenization for Image Generation

Beyond Generation: Using Multimodal LLMs as Detectors of LLM-Generated Deepfake Facial Images

REKI: Registering Knowledge in VLAs

WEAVE: Weaving Real-World Code Evolution into Dependency-Structured Tasks for Benchmarking and Training Code Agents

Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection

Discovering state-of-the-art quantum circuits with large language models

Scene Reconstruction Using Ubiquitous Wireless Signals via Diffusion Posterior Inference Over physics-Grounded Representations

3DCodeVerse: Exploring 3D Worlds as Code

Visual Sanad: Auditing Vision-Language Models for False Acceptance of Qur'anic Citations

Latent Compaction with Test-Time Training

How to Train Your Little Dragon: Teaching a Small Language Model to Construct and Refine GPU Optimization Scripts

Stateful Testing for Deep Learning Compilers

The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks

Unfragmenting Nawatl NMT: Single-Variant Specialization for Masewalkopa

Revisiting Simple Baselines for Relational Deep Learning

No tagged papers yet

No tagged papers yet

No tagged papers yet