language models
AI systems trained on text data to understand, generate, and predict human language, enabling various applications such as translation, summarization, and dialogue systems.
- AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners
- AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?
- Are Language Models Efficient Reasoners? A Perspective from Logic Programming
- Better Estimation of the Kullback--Leibler Divergence Between Language Models
- Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning
- Brain-Informed Fine-Tuning for Improved Multilingual Understanding in Language Models
- Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations
- CALM: Culturally Self-Aware Language Models
- CLEVER: A Curated Benchmark for Formally Verified Code Generation
- Compositional Reasoning with Transformers, RNNs, and Chain of Thought
- Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models
- Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective
- Explainable Reinforcement Learning from Human Feedback to Improve Alignment
- Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
- From Style to Facts: Mapping the Boundaries of Knowledge Injection with Finetuning
- GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents
- Improved Representation Steering for Language Models
- In Search of Adam’s Secret Sauce
- Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
- Knowledge Distillation of Uncertainty using Deep Latent Factor Model
- Language Models Can Predict Their Own Behavior
- Learning to Better Search with Language Models via Guided Reinforced Self-Training
- Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
- Mixtures of Subspaces for Bandwidth Efficient Context Parallel Training
- NaDRO: Leveraging Dual-Reward Strategies for LLMs Training on Noisy Data
- NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning
- Nested Learning: The Illusion of Deep Learning Architectures
- Neural Networks for Learnable and Scalable Influence Estimation of Instruction Fine-Tuning Data
- Order-Level Attention Similarity Across Language Models: A Latent Commonality
- Predicting the Performance of Black-box Language Models with Follow-up Queries
- Privacy Reasoning in Ambiguous Contexts
- RADAR: Benchmarking Language Models on Imperfect Tabular Data
- Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference
- Repo2Run: Automated Building Executable Environment for Code Repository at Scale
- Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates
- Rethinking the Role of Verbatim Memorization in LLM Privacy
- Robust Federated Finetuning of LLMs via Alternating Optimization of LoRA
- SWE-smith: Scaling Data for Software Engineering Agents
- Scalable Valuation of Human Feedback through Provably Robust Model Alignment
- Sheetpedia: A 300K-Spreadsheet Corpus for Spreadsheet Intelligence and LLM Fine-Tuning
- SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement
- Steering Generative Models with Experimental Data for Protein Fitness Optimization
- Steering Information Utility in Key-Value Memory for Language Model Post-Training
- The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning
- TokenSwap: A Lightweight Method to Disrupt Memorized Sequences in LLMs
- Towards General Continuous Memory for Vision-Language Models
- Understanding outer learning rates in Local SGD