Chen Ma

Spatial CAPTCHA: Generatively Benchmarking Spatial Reasoning for Human-Machine Differentiation

PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery

Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillation

Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling

CORE: Lossless Compression for Retrieval-Augmented LLMs via Reinforcement Learning

SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modeling

Understanding Before Evaluation: A Reliable Framework for Assessing Non-Deterministic Machine Translation Systems

Grounding Long-Context Reasoning with Contextual Normalization for Retrieval-Augmented Generation

Invariant Deep Uplift Modeling for Incentive Assignment in Online Marketing via Probability of Necessity and Sufficiency

Decision Information Meets Large Language Models: The Future of Explainable Operations Research

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks

RevisEval: Improving LLM-as-a-Judge via Response-Adapted References

Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization

SRA-CL: Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation

PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery

PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery

Decision Rules are in the Pixels: Towards Pixel-level Evaluation of Saliency-based XAI Models