{"total":29,"rows":[{"id":"2406.00877","title":"Evidence of Learned Look-Ahead in a Chess-Playing Neural Network","created":"2024-06-02","cited_by_count":34,"area":null},{"id":"2503.02854","title":"(How) Do Language Models Track State?","created":"2025-03-04","cited_by_count":34,"area":null},{"id":"2406.11741","title":"Transcendence: Generative Models Can Outperform The Experts That Train Them","created":"2024-06-17","cited_by_count":20,"area":null},{"id":"2407.15421","title":"Planning in a recurrent neural network that plays Sokoban","created":"2024-07-22","cited_by_count":18,"area":null},{"id":"2410.03893","title":"Human-aligned Chess with a Bit of Search","created":"2024-10-04","cited_by_count":11,"area":null},{"id":"2503.13401","title":"Levels of Analysis for Large Language Models","created":"2025-03-17","cited_by_count":10,"area":null},{"id":"2505.14925","title":"Too Long, Didn't Model: Decomposing LLM Long-Context Understanding With Novels","created":"2025-05-20","cited_by_count":9,"area":null},{"id":"2410.03020","title":"On Logical Extrapolation for Mazes with Recurrent and Implicit Networks","created":"2024-10-03","cited_by_count":7,"area":null},{"id":"2605.19091","title":"Chessformer: A Unified Architecture for Chess Modeling","created":"2026-05-18","cited_by_count":6,"area":null},{"id":"2605.30233","title":"Do Language Models Track Entities Across State Changes?","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2509.17280","title":"From Prediction to Understanding: Will AI Foundation Models Transform Brain Science?","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2602.04447","title":"Mixture of Masters: Sparse Chess Language Models with Player Routing","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2605.12809","title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2609.14011","title":"Convergent Emergence of In-Context Learning Across Modalities","created":"2026-09-12","cited_by_count":1,"area":null},{"id":"2505.21552","title":"Understanding the learned look-ahead behavior of chess neural networks","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2507.14520","title":"What if Othello-Playing Language Models Could See?","created":"2025-07-19","cited_by_count":0,"area":null},{"id":"2510.27009","title":"Causal Masking on Spatial Data: An Information-Theoretic Case for Learning Spatial Datasets with Unimodal Language Models","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2602.01716","title":"Mechanistic Indicators of Steering Effectiveness in Large Language Models","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.14087","title":"Understanding the Emergence of Seemingly Useless Features in Next-Token Predictors","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.29761","title":"Tracking vs. Deciding: The Dual-Capability Bottleneck in Searchless Chess Transformers","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.04899","title":"A geometric relation of the error introduced by sampling a language model's output distribution to its internal state","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.27767","title":"UniMaia: Steering Chess Policies with Language for Human-like Play","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.10248","title":"One mechanism for many mental spaces: a shared router over a value slot in language models","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.11953","title":"When Does Reward Teach State? A Hidden-Automaton Instrument and a Group-Language Warning Signal","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2609.23917","title":"Increasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.24352","title":"Few-Shot Demonstrations Elicit the Use of In-Context World Representations in LLMs","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.38718","title":"MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00416","title":"Benchmarking Prompt Optimization of Large Language Models With Chess","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.12847","title":"When Generative Models Act as Simulators","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}