{"list":"other","total":63,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040},{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939},{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494},{"id":"1511.06295","title":"Policy Distillation","created":"2015-11-19","cited_by_count":440},{"id":"2506.04178","title":"OpenThoughts: Data Recipes for Reasoning Models","created":"2025-06-04","cited_by_count":304},{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281},{"id":"2402.13446","title":"Large Language Models for Data Annotation and Synthesis: A Survey","created":"2024-02-21","cited_by_count":205},{"id":"2605.00674","title":"Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs","created":"2026-05-01","cited_by_count":137},{"id":"2502.01534","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","created":"2025-02-03","cited_by_count":125},{"id":"2402.19449","title":"Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models","created":"2024-02-29","cited_by_count":80},{"id":"2403.20046","title":"Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning","created":"2024-03-29","cited_by_count":69},{"id":"2507.02939","title":"Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting","created":"2025-06-27","cited_by_count":55},{"id":"2601.03236","title":"MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents","created":"2026-01-06","cited_by_count":52},{"id":"2503.21309","title":"FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval","created":"2025-03-27","cited_by_count":42},{"id":"2604.17898","title":"ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval","created":"2026-04-20","cited_by_count":41},{"id":"2509.12662","title":"Chat-Driven Text Generation and Interaction for Person Retrieval","created":"2025-09-16","cited_by_count":34},{"id":"2505.12079","title":"SepPrune: Structured Pruning for Efficient Deep Speech Separation","created":"2025-05-17","cited_by_count":31},{"id":"2505.13975","title":"DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models","created":"2025-05-20","cited_by_count":30},{"id":"2410.14720","title":"SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Models","created":"2024-10-14","cited_by_count":25},{"id":"2604.18037","title":"HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval","created":"2026-04-20","cited_by_count":24},{"id":"2601.12768","title":"Delving Deeper: Hierarchical Visual Perception for Robust Video-Text Retrieval","created":"2026-01-19","cited_by_count":23},{"id":"2601.03555","title":"SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models","created":"2026-01-07","cited_by_count":21},{"id":"2602.19320","title":"Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations","created":"2026-02-22","cited_by_count":21},{"id":"2603.16877","title":"Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysis","created":"2026-02-18","cited_by_count":21},{"id":"2603.22446","title":"Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs","created":"2026-03-23","cited_by_count":20},{"id":"2402.01729","title":"Contextualization Distillation from Large Language Model for Knowledge Graph Completion","created":"2024-01-28","cited_by_count":18},{"id":"2604.19386","title":"Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval","created":"2026-04-21","cited_by_count":18},{"id":"2512.02924","title":"AutoNeural: Co-Designing Vision-Language Models for NPU Inference","created":"2025-12-02","cited_by_count":17},{"id":"2604.20358","title":"ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval","created":"2026-04-22","cited_by_count":17},{"id":"2402.16424","title":"COMAE: COMprehensive Attribute Exploration for Zero-shot Hashing","created":"2024-02-26","cited_by_count":16},{"id":"2510.18871","title":"How Do LLMs Use Their Depth?","created":"2025-10-21","cited_by_count":16},{"id":"2509.23292","title":"Learning How to Use Tools, Not Just When: Pattern-Aware Tool-Integrated Reasoning","created":"2025-09-27","cited_by_count":15},{"id":"2510.10925","title":"Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation","created":"2025-10-13","cited_by_count":15},{"id":"2603.21389","title":"Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models","created":"2026-03-22","cited_by_count":15},{"id":"2604.21806","title":"TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval","created":"2026-04-23","cited_by_count":15},{"id":"2501.14315","title":"Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning","created":"2025-01-24","cited_by_count":14},{"id":"2505.19653","title":"Token-Importance Guided Direct Preference Optimization","created":"2025-05-26","cited_by_count":14},{"id":"2601.16155","title":"HVD: Human Vision-Driven Video Representation Learning for Text-Video Retrieval","created":"2026-01-22","cited_by_count":14},{"id":"2511.17448","title":"MMT-ARD: Multimodal Multi-Teacher Adversarial Distillation for Robust Vision-Language Models","created":"2025-11-21","cited_by_count":11},{"id":"2601.12785","title":"Distilling Time Series Foundation Models for Efficient Forecasting","created":"2026-01-19","cited_by_count":11},{"id":"2509.05764","title":"DRF: LLM-AGENT Dynamic Reputation Filtering Framework","created":"2025-09-06","cited_by_count":10},{"id":"2509.13723","title":"DSPC: Dual-Stage Progressive Compression Framework for Efficient Long-Context Reasoning","created":"2025-09-17","cited_by_count":10},{"id":"2509.26614","title":"Hy-Facial: Hybrid Feature Extraction by Dimensionality Reduction Methods for Enhanced Facial Expression Classification","created":"2025-09-30","cited_by_count":10},{"id":"2605.08060","title":"The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents","created":"2026-05-08","cited_by_count":10},{"id":"2301.04850","title":"Understanding Difficulty-based Sample Weighting with a Universal Difficulty Measure","created":"2023-01-12","cited_by_count":9},{"id":"2506.17290","title":"SRKD: Towards Efficient 3D Point Cloud Segmentation via Structure- and Relation-aware Knowledge Distillation","created":"2025-06-16","cited_by_count":9},{"id":"2601.06853","title":"DAGGER: Distractor-Aware Graph Generation for Executable Reasoning in Math Problems","created":"2026-01-11","cited_by_count":9},{"id":"2603.28618","title":"Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning","created":"2026-03-30","cited_by_count":9},{"id":"2511.23402","title":"Quantized-Tinyllava: a new multimodal foundation model enables efficient split learning","created":"2025-11-28","cited_by_count":8},{"id":"2509.12638","title":"FinSentLLM: Multi-LLM and Structured Semantic Signals for Enhanced Financial Sentiment Forecasting","created":"2025-09-16","cited_by_count":7},{"id":"2511.16715","title":"DDTime: Dataset Distillation with Spectral Alignment and Information Bottleneck for Time-Series Forecasting","created":"2025-11-20","cited_by_count":7},{"id":"2603.01875","title":"KDFlow: A User-Friendly and Efficient Knowledge Distillation Framework for Large Language Models","created":"2026-03-02","cited_by_count":7},{"id":"2408.05432","title":"Simpler is More: Efficient Top-K Nearest Neighbors Search on Large Road Networks","created":"2024-08-10","cited_by_count":6},{"id":"2601.06767","title":"GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO","created":"2026-01-11","cited_by_count":6},{"id":"2605.23924","title":"Improving the Completeness and Comparability of Segment Disclosures: A Large Language Model Approach","created":"2026-04-20","cited_by_count":6},{"id":"2602.22556","title":"Stable Adaptive Thinking via Advantage Shaping and Length-Aware Gradient Regulation","created":"2026-02-26","cited_by_count":4},{"id":"2603.14602","title":"PA3: Policy-Aware Agent Alignment through Chain-of-Thought","created":"2026-03-15","cited_by_count":4},{"id":"2602.11743","title":"Adaptive Debiasing Tsallis Entropy for Test-Time Adaptation","created":"2026-02-12","cited_by_count":3},{"id":"2605.05811","title":"Sheet As Token: A Graph-Enhanced Representation for Multi-Sheet Spreadsheet Understanding","created":"2026-05-07","cited_by_count":3}],"next_cursor":null}