4 papers
Watermarks for Language Models via Probabilistic Automata
Yangkun Wang, Jingbo Shang
A recent watermarking scheme for language models achieves distortion-free embedding and robustness to edit-distance attacks. However, it suffers from limited generation diversity a…
ReMem: Mutual Information-Aware Fine-tuning of Pretrained Vision Transformers for Effective Knowledge Distillation
Chengyu Dong, Huan Gui, Noveen Sachdeva +6
Knowledge distillation from pretrained visual representation models offers an effective approach to improve small, task-specific production models. However, the effectiveness of su…
VeriLocc: End-to-End Cross-Architecture Register Allocation via LLM
Lesheng Jin, Zhenyuan Ruan, Haohui Mai +1
Modern GPUs evolve rapidly, yet production compilers still rely on hand-crafted register allocation heuristics that require substantial re-tuning for each hardware generation. We i…
Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation
Zi Lin, Sheng Shen, Ilia Kulikov +3
Recent advances in large language models (LLMs) have improved their performance on coding benchmarks. However, improvement is plateauing due to the exhaustion of readily available…