{"total":114,"rows":[{"id":"2303.12501","title":"Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval","created":"2023-03-22","cited_by_count":132,"area":"lr"},{"id":"2507.08838","title":"wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models","created":"2025-07-07","cited_by_count":71,"area":"lr"},{"id":"2402.11451","title":"SciAgent: Tool-augmented Language Models for Scientific Reasoning","created":"2024-02-18","cited_by_count":70,"area":"lr"},{"id":"2205.10712","title":"Housekeep: Tidying Virtual Households using Commonsense Reasoning","created":"2022-05-22","cited_by_count":57,"area":"lr"},{"id":"2310.15747","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","created":"2023-10-24","cited_by_count":51,"area":"lr"},{"id":"2207.04630","title":"On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence","created":"2022-07-11","cited_by_count":50,"area":"lr"},{"id":"2405.18634","title":"A Theoretical Understanding of Self-Correction through In-context Alignment","created":"2024-05-28","cited_by_count":44,"area":"lr"},{"id":"2310.08753","title":"CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models","created":"2023-10-12","cited_by_count":43,"area":"lr"},{"id":"2202.04800","title":"The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning","created":"2022-02-10","cited_by_count":38,"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":"2310.14478","title":"GeoLM: Empowering Language Models for Geospatially Grounded Language Understanding","created":"2023-10-23","cited_by_count":37,"area":"lr"},{"id":"2404.06347","title":"RAR-b: Reasoning as Retrieval Benchmark","created":"2024-04-09","cited_by_count":36,"area":"lr"},{"id":"2405.03000","title":"MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoning","created":"2024-05-05","cited_by_count":36,"area":"lr"},{"id":"2202.10284","title":"A Review of Emerging Research Directions in Abstract Visual Reasoning","created":"2022-02-21","cited_by_count":33,"area":"lr"},{"id":"2401.06800","title":"Reinforcement Learning for Optimizing RAG for Domain Chatbots","created":"2024-01-10","cited_by_count":26,"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":"2602.13823","title":"Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings","created":"2026-02-14","cited_by_count":24,"area":"lr"},{"id":"2508.00410","title":"Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models","created":"2025-08-01","cited_by_count":23,"area":"lr"},{"id":"2601.13879","title":"Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring","created":"2026-01-20","cited_by_count":21,"area":"lr"},{"id":"2505.20613","title":"REAL-Prover: Retrieval Augmented Lean Prover for Mathematical Reasoning","created":"2025-05-27","cited_by_count":18,"area":"lr"},{"id":"2305.02556","title":"Faithful Question Answering with Monte-Carlo Planning","created":"2023-05-04","cited_by_count":16,"area":"lr"},{"id":"2601.03595","title":"Controllable LLM Reasoning via Sparse Autoencoder-Based Steering","created":"2026-01-07","cited_by_count":15,"area":"lr"},{"id":"2604.02073","title":"PLUME: Latent Reasoning Based Universal Multimodal Embedding","created":"2026-04-02","cited_by_count":11,"area":"lr"},{"id":"2602.18297","title":"Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory","created":"2026-02-20","cited_by_count":10,"area":"lr"},{"id":"2312.07132","title":"Image Content Generation with Causal Reasoning","created":"2023-12-12","cited_by_count":9,"area":"lr"},{"id":"2309.11143","title":"CoT-BERT: Enhancing Unsupervised Sentence Representation through Chain-of-Thought","created":"2023-09-20","cited_by_count":8,"area":"lr"},{"id":"2505.19952","title":"Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval","created":"2025-05-26","cited_by_count":8,"area":"lr"},{"id":"2205.12616","title":"Guiding Visual Question Answering with Attention Priors","created":"2022-05-25","cited_by_count":7,"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":"2503.20576","title":"Optimizing Case-Based Reasoning System for Functional Test Script Generation with Large Language Models","created":"2025-03-26","cited_by_count":7,"area":"lr"},{"id":"2509.09154","title":"Mind Meets Space: Rethinking Agentic Spatial Intelligence from a Neuroscience-inspired Perspective","created":"2025-09-11","cited_by_count":7,"area":"lr"},{"id":"2510.04506","title":"GRACE: Generative Representation Learning via Contrastive Policy Optimization","created":"2025-10-06","cited_by_count":7,"area":"lr"},{"id":"2510.11056","title":"From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2510.19791","title":"ToolDreamer: Instilling LLM Reasoning Into Tool Retrievers","created":"2025-10-22","cited_by_count":7,"area":"lr"},{"id":"2603.02929","title":"TRACE: Task-Adaptive Reasoning and Representation Learning for Universal Multimodal Retrieval","created":"2026-03-03","cited_by_count":7,"area":"lr"},{"id":"2605.17672","title":"Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models","created":"2026-05-17","cited_by_count":7,"area":"lr"},{"id":"2508.13113","title":"Contrastive Representations for Temporal Reasoning","created":"2025-08-18","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":"2512.01223","title":"S$^2$-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance","created":"2025-12-01","cited_by_count":5,"area":"lr"},{"id":"2512.08135","title":"CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning","created":"2025-12-09","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":"2604.22280","title":"Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings","created":"2026-04-24","cited_by_count":5,"area":"lr"},{"id":"2606.13061","title":"LaME: Learning to Think in Latent Space for Multimodal Embedding via Information Bottleneck","created":"2026-06-11","cited_by_count":5,"area":"lr"},{"id":"2510.07048","title":"Search-R3: Unifying Reasoning and Embedding in Large Language Models","created":"2025-10-08","cited_by_count":4,"area":"lr"},{"id":"2507.06507","title":"GR-LLMs: Recent Advances in Generative Recommendation Based on Large Language Models","created":"2025-07-09","cited_by_count":3,"area":"lr"},{"id":"2508.03722","title":"Multimodal Video Emotion Recognition with Reliable Reasoning Priors","created":"2025-07-29","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":"2511.10240","title":"ProgRAG: Hallucination-Resistant Progressive Retrieval and Reasoning over Knowledge Graphs","created":"2025-11-13","cited_by_count":3,"area":"lr"},{"id":"2511.12081","title":"From Scaling to Structured Expressivity: Rethinking Transformers for CTR Prediction","created":"2025-11-15","cited_by_count":3,"area":"lr"},{"id":"2602.10622","title":"How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning","created":"2026-02-11","cited_by_count":3,"area":"lr"},{"id":"2603.05181","title":"Mario: Multimodal Graph Reasoning with Large Language Models","created":"2026-03-05","cited_by_count":3,"area":"lr"},{"id":"2604.07419","title":"ReAlign: Optimizing the Visual Document Retriever with Reasoning-Guided Fine-Grained Alignment","created":"2026-04-08","cited_by_count":3,"area":"lr"},{"id":"2605.14448","title":"Think When Needed: Adaptive Reasoning-Driven Multimodal Embeddings with a Dual-LoRA Architecture","created":"2026-05-14","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":"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":"2510.11278","title":"ENIGMA: The Geometry of Reasoning and Alignment in Large-Language Models","created":"2025-10-13","cited_by_count":2,"area":"lr"},{"id":"2511.00521","title":"Reasoning Planning for Language Models","created":"2025-11-01","cited_by_count":2,"area":"lr"},{"id":"2511.12008","title":"Adaptive Diagnostic Reasoning Framework for Pathology with Multimodal Large Language Models","created":"2025-11-15","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":"2511.19514","title":"SCoTER: Structured Chain-of-Thought Transfer for Enhanced Recommendation","created":"2025-11-24","cited_by_count":2,"area":"lr"},{"id":"2601.05549","title":"Efficient Temporal-aware Matryoshka Adaptation for Temporal Information Retrieval","created":"2026-01-09","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":"2307.08506","title":"Does Visual Pretraining Help End-to-End Reasoning?","created":"2023-07-17","cited_by_count":1,"area":"lr"},{"id":"2404.00051","title":"Deja vu: Contrastive Historical Modeling with Prefix-tuning for Temporal Knowledge Graph Reasoning","created":"2024-03-25","cited_by_count":1,"area":"lr"},{"id":"2505.22202","title":"Latent Reasoning via Sentence Embedding Prediction","created":"2025-05-28","cited_by_count":1,"area":"lr"},{"id":"2510.11217","title":"Domain-Specific Data Generation Framework for RAG Adaptation","created":"2025-10-13","cited_by_count":1,"area":"lr"},{"id":"2601.13797","title":"PREGEN: Uncovering Latent Thoughts in Composed Video Retrieval","created":"2026-01-20","cited_by_count":1,"area":"lr"},{"id":"2602.22296","title":"UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2603.06923","title":"Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping","created":"2026-03-06","cited_by_count":1,"area":"lr"},{"id":"2603.13884","title":"SCoCCA: Multi-modal Sparse Concept Decomposition via Canonical Correlation Analysis","created":"2026-03-14","cited_by_count":1,"area":"lr"},{"id":"2603.26049","title":"Seeing Like Radiologists: Context- and Gaze-Guided Vision-Language Pretraining for Chest X-rays","created":"2026-03-27","cited_by_count":1,"area":"lr"},{"id":"2604.10949","title":"Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models","created":"2026-04-13","cited_by_count":1,"area":"lr"},{"id":"2604.20283","title":"Multi-Perspective Evidence Synthesis and Reasoning for Unsupervised Multimodal Entity Linking","created":"2026-04-22","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":"2607.23802","title":"From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement","created":"2026-07-26","cited_by_count":1,"area":"lr"},{"id":"2609.08242","title":"CS-CLIP: Compositional Scene Graph-guided CLIP for Robust Compositional Reasoning","created":"2026-09-08","cited_by_count":1,"area":"lr"},{"id":"2310.06803","title":"Advancing Transformer's Capabilities in Commonsense Reasoning","created":"2023-10-10","cited_by_count":0,"area":"lr"},{"id":"2406.00307","title":"HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model","created":"2024-06-01","cited_by_count":0,"area":"lr"},{"id":"2506.01970","title":"Johnny: Structuring Representation Space to Enhance Machine Abstract Reasoning Ability","created":"2025-05-13","cited_by_count":0,"area":"lr"},{"id":"2509.18169","title":"PiERN: Token-Level Routing for Integrating High-Precision Computation and Reasoning","created":"2025-09-17","cited_by_count":0,"area":"lr"},{"id":"2510.08003","title":"CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning","created":"2025-10-09","cited_by_count":0,"area":"lr"},{"id":"2512.11680","title":"Cross-modal Context-aware Learning for Visual Prompt Guided Multimodal Image Understanding in Remote Sensing","created":"2025-12-12","cited_by_count":0,"area":"lr"},{"id":"2601.21192","title":"Do Reasoning Models Enhance Embedding Models?","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2601.21436","title":"From Consistency to Complementarity: Aligned and Disentangled Multi-modal Learning for Time Series Understanding and Reasoning","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2602.01554","title":"InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2603.01125","title":"Predictive Reasoning with Augmented Anomaly Contrastive Learning for Compositional Visual Relations","created":"2026-03-01","cited_by_count":0,"area":"lr"},{"id":"2603.17980","title":"Feeling the Space: Egomotion-Aware Video Representation for Efficient and Accurate 3D Scene Understanding","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2603.29405","title":"Hallucination-aware intermediate representation edit in large vision-language models","created":"2026-03-31","cited_by_count":0,"area":"lr"},{"id":"2604.17574","title":"Beyond Fine-Tuning: In-Context Learning and Chain-of-Thought for Reasoned Distractor Generation","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2605.06285","title":"LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2605.06906","title":"TraXion: Rethinking Pre-training Frameworks for Mobility and Beyond","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2605.11726","title":"Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.16899","title":"LASAR: Towards Spatio-temporal Reasoning with Latent Cognitive Map","created":"2026-05-16","cited_by_count":0,"area":"lr"},{"id":"2605.24674","title":"Reasoning to Align: Implicit Reasoning in Diffusion Transformers for Video Editing","created":"2026-05-23","cited_by_count":0,"area":"lr"},{"id":"2606.09033","title":"CRANE: Knowledge Editing for Reasoning MLLMs","created":"2026-06-08","cited_by_count":0,"area":"lr"},{"id":"2606.12847","title":"Language-Guided Abstraction for Visual Reasoning","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2606.17298","title":"Reasoning Text-to-Video Retrieval for Operating Room Clips via Action-Driven Digital Twins","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2606.31467","title":"AeroVerse-SatAgent: UAV-Satellite Collaborative Spatial Reasoning Inspired by the Dual Visual Pathway Theory of Cognitive Neuroscience","created":"2026-06-30","cited_by_count":0,"area":"lr"},{"id":"2607.18470","title":"RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts","created":"2026-07-20","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}