llms

Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens ICML 2025 Instruction-Following Pruning for Large Language Models ICML 2025 Interpreting the Repeated Token Phenomenon in Large Language Models ICML 2025 Investigating the Overlooked Hessian Structure: From CNNs to LLMs ICML 2025 KernelBench: Can LLMs Write Efficient GPU Kernels? ICML 2025 Large Language-Geometry Model: When LLM meets Equivariance ICML 2025 LLM-Augmented Chemical Synthesis and Design Decision Programs ICML 2025 LLMs can see and hear without any training ICML 2025 LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws ICML 2025 LOGO — Long cOntext aliGnment via efficient preference Optimization ICML 2025 LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits ICML 2025 MA-LoT: Model-Collaboration Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving ICML 2025 MATH-Perturb: Benchmarking LLMs’ Math Reasoning Abilities against Hard Perturbations ICML 2025 Mind the Gap: A Practical Attack on GGUF Quantization ICML 2025 Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing ICML 2025 Otter: Generating Tests from Issues to Validate SWE Patches ICML 2025 Peripheral Memory for LLMs: Integration of Sequential Memory Banks with Adaptive Querying ICML 2025 POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval ICML 2025 Position: Enough of Scaling LLMs! Lets Focus on Downscaling ICML 2025 Position: The Most Expensive Part of an LLM *should* be its Training Data ICML 2025 Private Federated Learning using Preference-Optimized Synthetic Data ICML 2025 ProofAug: Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis ICML 2025 RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals ICML 2025 Reducing Tool Hallucination via Reliability Alignment ICML 2025 RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation ICML 2025