{"list":"other","total":84,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1711.09601","title":"Memory Aware Synapses: Learning what (not) to forget","created":"2017-11-27","cited_by_count":1105},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"1812.00420","title":"Efficient Lifelong Learning with A-GEM","created":"2018-12-02","cited_by_count":1058},{"id":"2004.07211","title":"Dark Experience for General Continual Learning: a Strong, Simple Baseline","created":"2020-04-15","cited_by_count":911},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"2308.08747","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2023-08-17","cited_by_count":639},{"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":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"2402.14804","title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","created":"2024-02-22","cited_by_count":526},{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512},{"id":"2312.14135","title":"V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs","created":"2023-12-21","cited_by_count":482},{"id":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459},{"id":"2407.11691","title":"VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models","created":"2024-07-16","cited_by_count":455},{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415},{"id":"2003.12462","title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","created":"2020-03-24","cited_by_count":400},{"id":"2407.12772","title":"LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models","created":"2024-07-17","cited_by_count":353},{"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":"2506.06941","title":"The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity","created":"2025-06-07","cited_by_count":302},{"id":"2307.04964","title":"Secrets of RLHF in Large Language Models Part I: PPO","created":"2023-07-11","cited_by_count":229},{"id":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215},{"id":"2010.06808","title":"Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout","created":"2020-10-14","cited_by_count":201},{"id":"2501.00321","title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","created":"2024-12-31","cited_by_count":173},{"id":"2105.05486","title":"TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text","created":"2021-05-12","cited_by_count":171},{"id":"2504.13914","title":"Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning","created":"2025-04-10","cited_by_count":161},{"id":"2504.07934","title":"SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement","created":"2025-04-10","cited_by_count":145},{"id":"2309.10105","title":"Understanding Catastrophic Forgetting in Language Models via Implicit Inference","created":"2023-09-18","cited_by_count":144},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135},{"id":"2504.07954","title":"Perception-R1: Pioneering Perception Policy with Reinforcement Learning","created":"2025-04-10","cited_by_count":120},{"id":"2403.01244","title":"Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal","created":"2024-03-02","cited_by_count":118},{"id":"2412.07755","title":"SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models","created":"2024-12-10","cited_by_count":114},{"id":"2111.10603","title":"Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning","created":"2021-11-20","cited_by_count":101},{"id":"2507.06448","title":"Perception-Aware Policy Optimization for Multimodal Reasoning","created":"2025-07-08","cited_by_count":99},{"id":"2306.03792","title":"FAMO: Fast Adaptive Multitask Optimization","created":"2023-06-06","cited_by_count":78},{"id":"2503.21934","title":"Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad","created":"2025-03-27","cited_by_count":74},{"id":"2305.19000","title":"Independent Component Alignment for Multi-Task Learning","created":"2023-05-30","cited_by_count":70},{"id":"2401.08276","title":"AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception","created":"2024-01-16","cited_by_count":65},{"id":"2505.23646","title":"Are Reasoning Models More Prone to Hallucination?","created":"2025-05-29","cited_by_count":64},{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58},{"id":"2311.16206","title":"Continual Instruction Tuning for Large Multimodal Models","created":"2023-11-27","cited_by_count":49},{"id":"2502.15806","title":"A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos","created":"2025-02-19","cited_by_count":43},{"id":"2412.00947","title":"VisOnlyQA: Large Vision Language Models Still Struggle with Visual Perception of Geometric Information","created":"2024-12-01","cited_by_count":39},{"id":"2410.05474","title":"R-Bench: Are your Large Multimodal Model Robust to Real-world Corruptions?","created":"2024-10-07","cited_by_count":30},{"id":"2505.24871","title":"MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning","created":"2025-05-30","cited_by_count":30},{"id":"2505.08311","title":"AM-Thinking-v1: Advancing the Frontier of Reasoning at 32B Scale","created":"2025-05-13","cited_by_count":29},{"id":"2505.23558","title":"Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual Information","created":"2025-05-29","cited_by_count":28},{"id":"2505.06538","title":"Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model","created":"2025-05-10","cited_by_count":19},{"id":"2502.16182","title":"IPO: Your Language Model is Secretly a Preference Classifier","created":"2025-02-22","cited_by_count":17},{"id":"2211.13723","title":"Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective","created":"2022-11-24","cited_by_count":15},{"id":"2206.01934","title":"Stochastic Multiple Target Sampling Gradient Descent","created":"2022-06-04","cited_by_count":14},{"id":"2506.06130","title":"Gradient Similarity Surgery in Multi-Task Deep Learning","created":"2025-06-06","cited_by_count":5},{"id":"2509.23915","title":"Revisit the Imbalance Optimization in Multi-task Learning: An Experimental Analysis","created":"2025-09-28","cited_by_count":3}],"next_cursor":null}