Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers

Towards Autonomous and Auditable Medical Imaging Model Development

MUSCRIPTOR: AN OPEN MODEL FOR MULTI-INSTRUMENT MUSIC TRANSCRIPTION

Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms

Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution

Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

The Role of Rigor in Artificial Intelligence

Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals

Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning

LLM-Guided Program Evolution for Targeted Black-Box Attacks on Perceptual Hash Algorithms

Are LLMs ready for HARDCHOICES?

Prezta: Provable Remote Execution of Zero-Trust Authorization using SNARKs

Score-Only Distillation for Compact Dense Retrieval

FAIR GraphRAG: A Retrieval-Augmented Generation Approach for Semantic Data Analysis

ManiScope: LLM-Assisted Visual Analytics of Cryptocurrency Manipulation Risk

Event-based Neural Decoding for Neuroprosthetic Motor Control

Unlocking Every Expert in Domain-Specific Training

EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments

ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation

PithTrain: A Compact and Agent-Native MoE Training System

Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories

HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better

From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models

KronQ: LLM Quantization via Kronecker-Factored Hessian

Trust Region Policy Distillation

Video Generation Models are General-Purpose Vision Learners

Scalable Visual Pretraining for Language Intelligence

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL

Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers

Towards Autonomous and Auditable Medical Imaging Model Development

MUSCRIPTOR: AN OPEN MODEL FOR MULTI-INSTRUMENT MUSIC TRANSCRIPTION

Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms

Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution

Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

The Role of Rigor in Artificial Intelligence

Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals

Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning

LLM-Guided Program Evolution for Targeted Black-Box Attacks on Perceptual Hash Algorithms

Are LLMs ready for HARDCHOICES?

Prezta: Provable Remote Execution of Zero-Trust Authorization using SNARKs

Score-Only Distillation for Compact Dense Retrieval

FAIR GraphRAG: A Retrieval-Augmented Generation Approach for Semantic Data Analysis

ManiScope: LLM-Assisted Visual Analytics of Cryptocurrency Manipulation Risk

Event-based Neural Decoding for Neuroprosthetic Motor Control

Unlocking Every Expert in Domain-Specific Training

EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments

ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation

PithTrain: A Compact and Agent-Native MoE Training System

Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories

HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better

From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models

KronQ: LLM Quantization via Kronecker-Factored Hessian

Trust Region Policy Distillation

Video Generation Models are General-Purpose Vision Learners

Scalable Visual Pretraining for Language Intelligence

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL