Bin CUI

Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions

PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learning

SAS-Bench: A Fine-Grained Benchmark for Evaluating Short Answer Scoring with Large Language Models

SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling

FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding

Quantization Meets Sparsification for Faster Image Generation

SQLGovernor: An LLM-powered SQL Toolkit for Real World Application

NetMoE: Accelerating MoE Training through Dynamic Sample Placement

IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation

SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction

Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning

HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation

Consistency Flow Matching: Defining Straight Flows with Velocity Consistency

SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget

Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training

Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs

Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training

SysBench: Can LLMs Follow System Message?

Transfer learning in Scalable Graph Neural Network for Improved Physical Simulation

Enhancing Unsupervised Sentence Embeddings via Knowledge-Driven Data Augmentation and Gaussian-Decayed Contrastive Learning

MathScape: Evaluating MLLMs in Multi-modal Math Scenarios through a Hierarchical Benchmark

FB-Bench: A Fine-Grained Multi-Task Benchmark for Evaluating LLMs' Responsiveness to Human Feedback

PAS: Plug-and-Play Prompt Augmentation System