{"total":55,"rows":[{"id":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164,"area":"lr"},{"id":"2411.19943","title":"Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability","created":"2024-11-29","cited_by_count":83,"area":"lr"},{"id":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80,"area":"lr"},{"id":"2406.08527","title":"Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning","created":"2024-06-12","cited_by_count":49,"area":"lr"},{"id":"2510.27606","title":"Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning","created":"2025-10-31","cited_by_count":41,"area":"lr"},{"id":"2201.12382","title":"Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices","created":"2022-01-28","cited_by_count":37,"area":"lr"},{"id":"2503.19312","title":"ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning","created":"2025-03-25","cited_by_count":37,"area":"lr"},{"id":"2302.10258","title":"Neural Algorithmic Reasoning with Causal Regularisation","created":"2023-02-20","cited_by_count":31,"area":"lr"},{"id":"2510.00977","title":"It Takes Two: Your GRPO Is Secretly DPO","created":"2025-10-01","cited_by_count":26,"area":"lr"},{"id":"2311.16476","title":"LANS: A Layout-Aware Neural Solver for Plane Geometry Problem","created":"2023-11-25","cited_by_count":24,"area":"lr"},{"id":"2501.04670","title":"Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs","created":"2025-01-08","cited_by_count":16,"area":"lr"},{"id":"2508.12531","title":"Rethinking Safety in LLM Fine-tuning: An Optimization Perspective","created":"2025-08-17","cited_by_count":14,"area":"lr"},{"id":"2601.05729","title":"TAGRPO: Boosting GRPO on Image-to-Video Generation with Direct Trajectory Alignment","created":"2026-01-09","cited_by_count":10,"area":"lr"},{"id":"2505.13346","title":"J4R: Learning to Judge with Equivalent Initial State Group Relative Policy Optimization","created":"2025-05-19","cited_by_count":9,"area":"lr"},{"id":"2511.16150","title":"Reasoning Guided Embeddings: Leveraging MLLM Reasoning for Improved Multimodal Retrieval","created":"2025-11-20","cited_by_count":9,"area":"lr"},{"id":"2210.14914","title":"Multi-Viewpoint and Multi-Evaluation with Felicitous Inductive Bias Boost Machine Abstract Reasoning Ability","created":"2022-10-26","cited_by_count":7,"area":"lr"},{"id":"2406.17520","title":"Tell Me Where You Are: Multimodal LLMs Meet Place Recognition","created":"2024-06-25","cited_by_count":7,"area":"lr"},{"id":"2510.16416","title":"SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning","created":"2025-10-18","cited_by_count":7,"area":"lr"},{"id":"2210.07570","title":"MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation","created":"2022-10-14","cited_by_count":6,"area":"lr"},{"id":"2405.17062","title":"UniICL: An Efficient Unified Framework Unifying Compression, Selection, and Generation","created":"2024-05-27","cited_by_count":6,"area":"lr"},{"id":"2603.04772","title":"TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings","created":"2026-03-05","cited_by_count":6,"area":"lr"},{"id":"2311.05298","title":"Improving Vision-and-Language Reasoning via Spatial Relations Modeling","created":"2023-11-09","cited_by_count":5,"area":"lr"},{"id":"2603.10101","title":"CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR","created":"2026-03-10","cited_by_count":5,"area":"lr"},{"id":"2512.01822","title":"InnoGym: Benchmarking the Innovation Potential of AI Agents","created":"2025-12-01","cited_by_count":4,"area":"lr"},{"id":"2512.13070","title":"M-GRPO: Stabilizing Self-Supervised Reinforcement Learning for Large Language Models with Momentum-Anchored Policy Optimization","created":"2025-12-15","cited_by_count":4,"area":"lr"},{"id":"2305.13585","title":"Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs","created":"2023-05-23","cited_by_count":3,"area":"lr"},{"id":"2509.23183","title":"ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without Collapse","created":"2025-09-27","cited_by_count":3,"area":"lr"},{"id":"2302.14431","title":"Efficient Masked Autoencoders with Self-Consistency","created":"2023-02-28","cited_by_count":2,"area":"lr"},{"id":"2404.16416","title":"Learning Discriminative Spatio-temporal Representations for Semi-supervised Action Recognition","created":"2024-04-25","cited_by_count":2,"area":"lr"},{"id":"2506.16805","title":"Co-VisiON: Co-Visibility ReasONing on Sparse Image Sets of Indoor Scenes","created":"2025-06-20","cited_by_count":2,"area":"lr"},{"id":"2511.15256","title":"GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement Learning","created":"2025-11-19","cited_by_count":2,"area":"lr"},{"id":"2603.22057","title":"SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning","created":"2026-03-23","cited_by_count":2,"area":"lr"},{"id":"2605.25443","title":"Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning Models","created":"2026-05-25","cited_by_count":2,"area":"lr"},{"id":"2212.01639","title":"Visual Question Answering From Another Perspective: CLEVR Mental Rotation Tests","created":"2022-12-03","cited_by_count":1,"area":"lr"},{"id":"2212.10292","title":"Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?","created":"2022-12-20","cited_by_count":1,"area":"lr"},{"id":"2305.12384","title":"From Patches to Objects: Exploiting Spatial Reasoning for Better Visual Representations","created":"2023-05-21","cited_by_count":1,"area":"lr"},{"id":"2307.08506","title":"Does Visual Pretraining Help End-to-End Reasoning?","created":"2023-07-17","cited_by_count":1,"area":"lr"},{"id":"2403.00352","title":"Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning","created":"2024-03-01","cited_by_count":1,"area":"lr"},{"id":"2502.06874","title":"Group Reasoning Emission Estimation Networks","created":"2025-02-08","cited_by_count":1,"area":"lr"},{"id":"2507.00754","title":"Enhancing Self-Supervised Visual Representation Learning via Low-Rank Adapted LLMs","created":"2025-07-01","cited_by_count":1,"area":"lr"},{"id":"2511.12446","title":"CoTBox-TTT: Grounding Medical VQA with Visual Chain-of-Thought Boxes During Test-time Training","created":"2025-11-16","cited_by_count":1,"area":"lr"},{"id":"2511.17755","title":"CORA: Consistency-Guided Semi-Supervised Framework for Reasoning Segmentation","created":"2025-11-21","cited_by_count":1,"area":"lr"},{"id":"2601.11729","title":"SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models","created":"2026-01-16","cited_by_count":1,"area":"lr"},{"id":"2604.12966","title":"Boosting Visual Instruction Tuning with Self-Supervised Guidance","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2605.06650","title":"Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2605.12969","title":"Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2605.30861","title":"Distilling LLM Feedback for Lean Theorem Proving","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.02321","title":"Training-Free Composed Video Retrieval via Visual Representation-Guided Video-LLM Reasoning","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2403.03452","title":"D4C: Improving Negative Example Quality to Enhance Machine Abstract Reasoning Ability","created":"2024-03-06","cited_by_count":0,"area":"lr"},{"id":"2405.16860","title":"Think Before You Act: A Two-Stage Framework for Mitigating Gender Bias Towards Vision-Language Tasks","created":"2024-05-27","cited_by_count":0,"area":"lr"},{"id":"2508.11272","title":"Enhancing Supervised Composed Image Retrieval via Reasoning-Augmented Representation Engineering","created":"2025-08-15","cited_by_count":0,"area":"lr"},{"id":"2508.13229","title":"RISE: Enhancing VLM Image Annotation with Self-Supervised Reasoning","created":"2025-08-17","cited_by_count":0,"area":"lr"},{"id":"2509.05553","title":"Using Contrastive Learning to Improve Two-Way Reasoning in Large Language Models: The Obfuscation Task as a Case Study","created":"2025-09-06","cited_by_count":0,"area":"lr"},{"id":"2512.04228","title":"Addressing Logical Fallacies In Scientific Reasoning From Large Language Models: Towards a Dual-Inference Training Framework","created":"2025-12-03","cited_by_count":0,"area":"lr"},{"id":"2606.02248","title":"Geometric Latent Reasoning Induces Shorter Generations in LLMs","created":"2026-06-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}