{"list":"other","total":51,"rows":[{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"2512.02556","title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","created":"2025-12-02","cited_by_count":815},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2403.14624","title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","created":"2024-03-21","cited_by_count":586},{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512},{"id":"2601.18734","title":"Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models","created":"2026-01-26","cited_by_count":455},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384},{"id":"2410.05243","title":"Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents","created":"2024-10-07","cited_by_count":382},{"id":"2504.08837","title":"VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning","created":"2025-04-10","cited_by_count":323},{"id":"2507.11473","title":"Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety","created":"2025-07-15","cited_by_count":249},{"id":"2409.14507","title":"A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders","created":"2024-09-22","cited_by_count":160},{"id":"2410.16198","title":"Improve Vision Language Model Chain-of-thought Reasoning","created":"2024-10-21","cited_by_count":136},{"id":"2505.15879","title":"GRIT: Teaching MLLMs to Think with Images","created":"2025-05-21","cited_by_count":125},{"id":"2503.09532","title":"SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability","created":"2025-03-12","cited_by_count":124},{"id":"2402.13950","title":"Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning","created":"2024-02-21","cited_by_count":110},{"id":"2507.05246","title":"When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors","created":"2025-07-07","cited_by_count":88},{"id":"2406.12030","title":"SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model","created":"2024-06-17","cited_by_count":85},{"id":"2512.18311","title":"Monitoring Monitorability","created":"2025-12-20","cited_by_count":58},{"id":"2502.14829","title":"Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps","created":"2025-02-20","cited_by_count":47},{"id":"2309.04461","title":"Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models","created":"2023-09-08","cited_by_count":45},{"id":"2504.21277","title":"Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models","created":"2025-04-30","cited_by_count":44},{"id":"2410.10563","title":"MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks","created":"2024-10-14","cited_by_count":41},{"id":"2506.09047","title":"Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs","created":"2025-06-10","cited_by_count":35},{"id":"2304.07919","title":"Chain of Thought Prompt Tuning in Vision Language Models","created":"2023-04-16","cited_by_count":34},{"id":"2505.13444","title":"ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models","created":"2025-05-19","cited_by_count":32},{"id":"2603.05706","title":"Reasoning Models Struggle to Control their Chains of Thought","created":"2026-03-05","cited_by_count":25},{"id":"2411.14982","title":"Large Multi-modal Models Can Interpret Features in Large Multi-modal Models","created":"2024-11-22","cited_by_count":23},{"id":"2510.19851","title":"Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability","created":"2025-10-21","cited_by_count":22},{"id":"2507.22928","title":"How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding","created":"2025-07-24","cited_by_count":19},{"id":"2510.27378","title":"Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity","created":"2025-10-31","cited_by_count":17},{"id":"2602.20710","title":"Counterfactual Simulation Training for Chain-of-Thought Faithfulness","created":"2026-02-24","cited_by_count":17},{"id":"2510.26418","title":"Chain-of-Thought Hijacking","created":"2025-10-30","cited_by_count":16},{"id":"2511.11584","title":"Output Supervision Can Obfuscate the Chain of Thought","created":"2025-10-11","cited_by_count":13},{"id":"2602.12506","title":"On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs","created":"2026-02-13","cited_by_count":11},{"id":"2602.18297","title":"Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory","created":"2026-02-20","cited_by_count":10},{"id":"2507.13362","title":"Enhancing Spatial Reasoning in Vision-Language Models via Chain-of-Thought Prompting and Reinforcement Learning","created":"2025-07-06","cited_by_count":9},{"id":"2511.08525","title":"Investigating CoT Monitorability in Large Reasoning Models","created":"2025-11-11","cited_by_count":9},{"id":"2602.11180","title":"Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future Directions","created":"2026-01-21","cited_by_count":8},{"id":"2603.28590","title":"MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models","created":"2026-03-30","cited_by_count":8},{"id":"2506.19257","title":"MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models","created":"2025-06-24","cited_by_count":7},{"id":"2502.18239","title":"Unveiling and Causalizing CoT: A Causal Pespective","created":"2025-02-25","cited_by_count":6},{"id":"2511.20994","title":"GuardTrace-VL: Detecting Unsafe Multimodel Reasoning via Iterative Safety Supervision","created":"2025-11-26","cited_by_count":4},{"id":"2606.25657","title":"Steering Vision-Language Models with Joint Sparse Autoencoders","created":"2026-06-24","cited_by_count":4},{"id":"2605.15257","title":"Training on Documents About Monitoring Leads to CoT Obfuscation","created":"2026-05-14","cited_by_count":3},{"id":"2603.18656","title":"Balanced Thinking: Improving Chain of Thought Training in Vision Language Models","created":"2026-03-19","cited_by_count":1}],"next_cursor":null}