{"total":66,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132,"area":"lr"},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599,"area":"lr"},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510,"area":"lr"},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642,"area":"lr"},{"id":"2411.10442","title":"Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization","created":"2024-11-15","cited_by_count":239,"area":"lr"},{"id":"2505.07608","title":"MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining","created":"2025-05-12","cited_by_count":121,"area":"lr"},{"id":"2507.00432","title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning","created":"2025-07-01","cited_by_count":106,"area":"lr"},{"id":"2308.04592","title":"Shepherd: A Critic for Language Model Generation","created":"2023-08-08","cited_by_count":97,"area":"lr"},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95,"area":"lr"},{"id":"2402.05808","title":"Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning","created":"2024-02-08","cited_by_count":65,"area":"lr"},{"id":"2602.11451","title":"LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation","created":"2026-02-11","cited_by_count":61,"area":"lr"},{"id":"2501.11284","title":"RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?","created":"2025-01-20","cited_by_count":60,"area":"lr"},{"id":"2310.04928","title":"Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU","created":"2023-10-07","cited_by_count":53,"area":"lr"},{"id":"2410.18517","title":"KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing","created":"2024-10-24","cited_by_count":41,"area":"lr"},{"id":"2505.10475","title":"Parallel Scaling Law for Language Models","created":"2025-05-15","cited_by_count":30,"area":"lr"},{"id":"2203.08480","title":"E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning","created":"2022-03-16","cited_by_count":28,"area":"lr"},{"id":"2205.12598","title":"RobustLR: Evaluating Robustness to Logical Perturbation in Deductive Reasoning","created":"2022-05-25","cited_by_count":22,"area":"lr"},{"id":"2509.23184","title":"PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space","created":"2025-09-27","cited_by_count":16,"area":"lr"},{"id":"2210.08590","title":"Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective","created":"2022-10-16","cited_by_count":14,"area":"lr"},{"id":"2210.12887","title":"Retrieval Augmentation for Commonsense Reasoning: A Unified Approach","created":"2022-10-23","cited_by_count":14,"area":"lr"},{"id":"2410.12881","title":"MIND: Math Informed syNthetic Dialogues for Pretraining LLMs","created":"2024-10-15","cited_by_count":14,"area":"lr"},{"id":"2204.07408","title":"Towards Fine-grained Causal Reasoning and QA","created":"2022-04-15","cited_by_count":13,"area":"lr"},{"id":"2310.09107","title":"GLoRE: Evaluating Logical Reasoning of Large Language Models","created":"2023-10-13","cited_by_count":13,"area":"lr"},{"id":"2402.03686","title":"Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification","created":"2024-02-06","cited_by_count":13,"area":"lr"},{"id":"2403.07872","title":"Rethinking Generative Large Language Model Evaluation for Semantic Comprehension","created":"2024-03-12","cited_by_count":13,"area":"lr"},{"id":"2205.08794","title":"LogiGAN: Learning Logical Reasoning via Adversarial Pre-training","created":"2022-05-18","cited_by_count":11,"area":"lr"},{"id":"2603.01914","title":"AdaPonderLM: Gated Pondering Language Models with Token-Wise Adaptive Depth","created":"2026-03-02","cited_by_count":10,"area":"lr"},{"id":"2205.00731","title":"Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning","created":"2022-05-02","cited_by_count":8,"area":"lr"},{"id":"2305.13718","title":"Exploring Self-supervised Logic-enhanced Training for Large Language Models","created":"2023-05-23","cited_by_count":8,"area":"lr"},{"id":"2403.09085","title":"Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance","created":"2024-03-14","cited_by_count":8,"area":"lr"},{"id":"2507.04348","title":"SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control","created":"2025-07-06","cited_by_count":7,"area":"lr"},{"id":"2412.03467","title":"Training-Free Mitigation of Language Reasoning Degradation After Multimodal Instruction Tuning","created":"2024-12-04","cited_by_count":6,"area":"lr"},{"id":"2305.14237","title":"HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision","created":"2023-05-23","cited_by_count":5,"area":"lr"},{"id":"2505.07293","title":"AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection","created":"2025-05-12","cited_by_count":5,"area":"lr"},{"id":"2606.19257","title":"DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models","created":"2026-06-17","cited_by_count":5,"area":"lr"},{"id":"2510.09426","title":"KORMo: Korean Open Reasoning Model for Everyone","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2602.08220","title":"Pretraining with Token-Level Adaptive Latent Chain-of-Thought","created":"2026-02-09","cited_by_count":4,"area":"lr"},{"id":"2602.11185","title":"Spectra: Rethinking Optimizers for LLMs Under Spectral Anisotropy","created":"2026-01-30","cited_by_count":4,"area":"lr"},{"id":"2603.02023","title":"PonderLM-3: Adaptive Token-Wise Pondering with Differentiable Masking","created":"2026-03-02","cited_by_count":4,"area":"lr"},{"id":"2209.07760","title":"Possible Stories: Evaluating Situated Commonsense Reasoning under Multiple Possible Scenarios","created":"2022-09-16","cited_by_count":3,"area":"lr"},{"id":"2210.07519","title":"Can Language Representation Models Think in Bets?","created":"2022-10-14","cited_by_count":3,"area":"lr"},{"id":"2210.11265","title":"Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers","created":"2022-10-20","cited_by_count":3,"area":"lr"},{"id":"2306.15273","title":"IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning","created":"2023-06-27","cited_by_count":3,"area":"lr"},{"id":"2605.05227","title":"Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods","created":"2026-04-19","cited_by_count":3,"area":"lr"},{"id":"2207.01450","title":"Discourse-Aware Graph Networks for Textual Logical Reasoning","created":"2022-07-04","cited_by_count":2,"area":"lr"},{"id":"2301.02983","title":"Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text","created":"2023-01-08","cited_by_count":2,"area":"lr"},{"id":"2305.14569","title":"Few-shot Unified Question Answering: Tuning Models or Prompts?","created":"2023-05-23","cited_by_count":2,"area":"lr"},{"id":"2312.11720","title":"Assessing Logical Reasoning Capabilities of Encoder-Only Transformer Models","created":"2023-12-18","cited_by_count":2,"area":"lr"},{"id":"2605.01959","title":"Flexi-LoRA with Input-Adaptive Ranks: Efficient Finetuning for Speech and Reasoning Tasks","created":"2026-05-03","cited_by_count":2,"area":"lr"},{"id":"2203.00160","title":"Semantic Sentence Composition Reasoning for Multi-Hop Question Answering","created":"2022-03-01","cited_by_count":1,"area":"lr"},{"id":"2306.12069","title":"Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension","created":"2023-06-21","cited_by_count":1,"area":"lr"},{"id":"2403.18230","title":"Large Language Models Need Consultants for Reasoning: Becoming an Expert in a Complex Human System Through Behavior Simulation","created":"2024-03-27","cited_by_count":1,"area":"lr"},{"id":"2410.13666","title":"VL-GLUE: A Suite of Fundamental yet Challenging Visuo-Linguistic Reasoning Tasks","created":"2024-10-17","cited_by_count":1,"area":"lr"},{"id":"2602.14649","title":"GradMAP: Faster Layer Pruning with Gradient Metric and Projection Compensation","created":"2026-02-16","cited_by_count":1,"area":"lr"},{"id":"2605.07353","title":"Confidence-Aware Alignment Makes Reasoning LLMs More Reliable","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.14754","title":"XDomainBench: Diagnosing Reasoning Collapse in High-Dimensional Scientific Knowledge Composition","created":"2026-05-14","cited_by_count":1,"area":"lr"},{"id":"2606.18453","title":"LLM Parameters for Math Across Languages: Shared or Separate?","created":"2026-06-16","cited_by_count":1,"area":"lr"},{"id":"2606.25832","title":"MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources","created":"2026-06-24","cited_by_count":1,"area":"lr"},{"id":"2210.15456","title":"JECC: Commonsense Reasoning Tasks Derived from Interactive Fictions","created":"2022-10-18","cited_by_count":0,"area":"lr"},{"id":"2505.11893","title":"RLAP: A Reinforcement Learning Enhanced Adaptive Planning Framework for Multi-step NLP Task Solving","created":"2025-05-17","cited_by_count":0,"area":"lr"},{"id":"2509.00465","title":"Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning","created":"2025-08-30","cited_by_count":0,"area":"lr"},{"id":"2509.09448","title":"TORSO: Template-Oriented Reasoning Towards General Tasks","created":"2025-09-11","cited_by_count":0,"area":"lr"},{"id":"2604.05757","title":"Identifying Influential N-grams in Confidence Calibration via Regression Analysis","created":"2026-04-07","cited_by_count":0,"area":"lr"},{"id":"2609.16055","title":"State of Thought Enables Endogenous Reasoning","created":"2026-09-13","cited_by_count":0,"area":"lr"},{"id":"2609.37169","title":"Trajectory Soup: Pushing the Compute-Scaling Frontier of LLM Mid-training via Diverse Trajectories","created":"2026-09-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}