{"total":232,"rows":[{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984,"area":null},{"id":"2412.19437","title":"DeepSeek-V3 Technical Report","created":"2024-12-27","cited_by_count":811,"area":"lr"},{"id":"2311.10723","title":"Large Language Models in Finance: A Survey","created":"2023-09-28","cited_by_count":226,"area":null},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209,"area":"mllm"},{"id":"2209.05433","title":"FP8 Formats for Deep Learning","created":"2022-09-12","cited_by_count":196,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159,"area":null},{"id":"2301.03728","title":"Scaling Laws for Generative Mixed-Modal Language Models","created":"2023-01-10","cited_by_count":134,"area":null},{"id":"2405.12981","title":"Reducing Transformer Key-Value Cache Size with Cross-Layer Attention","created":"2024-05-21","cited_by_count":131,"area":"inference"},{"id":"2405.04324","title":"Granite Code Models: A Family of Open Foundation Models for Code Intelligence","created":"2024-05-07","cited_by_count":117,"area":null},{"id":"2407.13690","title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","created":"2024-06-18","cited_by_count":95,"area":"lr"},{"id":"2403.12019","title":"LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation","created":"2024-03-18","cited_by_count":92,"area":null},{"id":"2301.02280","title":"Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training","created":"2023-01-05","cited_by_count":91,"area":"mllm"},{"id":"2205.09921","title":"KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation","created":"2022-05-20","cited_by_count":86,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2310.04415","title":"Why Do We Need Weight Decay in Modern Deep Learning?","created":"2023-10-06","cited_by_count":72,"area":null},{"id":"2510.26788","title":"Defeating the Training-Inference Mismatch via FP16","created":"2025-10-30","cited_by_count":66,"area":null},{"id":"2402.12030","title":"Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs","created":"2024-02-19","cited_by_count":63,"area":"distill"},{"id":"2302.09432","title":"BBT-Fin: Comprehensive Construction of Chinese Financial Domain Pre-trained Language Model, Corpus and Benchmark","created":"2023-02-18","cited_by_count":60,"area":null},{"id":"2406.04303","title":"Vision-LSTM: xLSTM as Generic Vision Backbone","created":"2024-06-06","cited_by_count":51,"area":null},{"id":"2302.08007","title":"With Shared Microexponents, A Little Shifting Goes a Long Way","created":"2023-02-16","cited_by_count":50,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2406.11831","title":"Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models","created":"2024-06-17","cited_by_count":45,"area":"diffusion"},{"id":"2110.10486","title":"A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays","created":"2021-10-20","cited_by_count":37,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2512.02010","title":"Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling","created":"2025-12-01","cited_by_count":35,"area":null},{"id":"2307.14995","title":"TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer","created":"2023-07-27","cited_by_count":34,"area":null},{"id":"2502.12970","title":"Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking","created":"2025-02-18","cited_by_count":34,"area":"lr"},{"id":"2410.19313","title":"COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training","created":"2024-10-25","cited_by_count":33,"area":null},{"id":"2405.17381","title":"Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention","created":"2024-05-27","cited_by_count":31,"area":null},{"id":"2405.15574","title":"Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models","created":"2024-05-24","cited_by_count":30,"area":"ssm"},{"id":"2404.10779","title":"Fine Tuning LLM for Enterprise: Practical Guidelines and Recommendations","created":"2024-03-23","cited_by_count":28,"area":null},{"id":"2506.08123","title":"QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA","created":"2025-06-09","cited_by_count":28,"area":"alignment"},{"id":"2410.16215","title":"Pre-training Distillation for Large Language Models: A Design Space Exploration","created":"2024-10-21","cited_by_count":27,"area":"distill"},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2206.02915","title":"8-bit Numerical Formats for Deep Neural Networks","created":"2022-06-06","cited_by_count":25,"area":null},{"id":"2402.00522","title":"Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling","created":"2024-02-01","cited_by_count":25,"area":null},{"id":"2504.11651","title":"70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)","created":"2025-04-15","cited_by_count":24,"area":"diffusion"},{"id":"2407.12327","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2502.20853","title":"Oscillation-Reduced MXFP4 Training for Vision Transformers","created":"2025-02-28","cited_by_count":21,"area":null},{"id":"2309.17224","title":"Training and inference of large language models using 8-bit floating point","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2406.17720","title":"BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity","created":"2024-06-25","cited_by_count":20,"area":null},{"id":"2405.18111","title":"ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator","created":"2024-05-28","cited_by_count":19,"area":"rag"},{"id":"2406.13555","title":"BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation","created":"2024-06-19","cited_by_count":19,"area":null},{"id":"2310.14424","title":"Which Prompts Make The Difference? Data Prioritization For Efficient Human LLM Evaluation","created":"2023-10-22","cited_by_count":18,"area":null},{"id":"2503.13551","title":"Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models","created":"2025-03-16","cited_by_count":18,"area":"lr"},{"id":"2303.11257","title":"Unit Scaling: Out-of-the-Box Low-Precision Training","created":"2023-03-20","cited_by_count":17,"area":null},{"id":"2409.14713","title":"Phantom of Latent for Large Language and Vision Models","created":"2024-09-23","cited_by_count":17,"area":null},{"id":"2505.14302","title":"Scaling Law for Quantization-Aware Training","created":"2025-05-20","cited_by_count":17,"area":null},{"id":"2505.16326","title":"ChemMLLM: Chemical Multimodal Large Language Model","created":"2025-05-22","cited_by_count":17,"area":"mllm"},{"id":"2509.04484","title":"The Good, the Bad and the Constructive: Automatically Measuring Peer Review's Utility for Authors","created":"2025-08-31","cited_by_count":16,"area":null},{"id":"2103.10891","title":"Accelerating SLIDE Deep Learning on Modern CPUs: Vectorization, Quantizations, Memory Optimizations, and More","created":"2021-03-06","cited_by_count":15,"area":null},{"id":"2206.07808","title":"Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems","created":"2022-06-15","cited_by_count":15,"area":"distill"},{"id":"2304.10520","title":"Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget","created":"2023-04-20","cited_by_count":15,"area":null},{"id":"2401.03804","title":"TeleChat Technical Report","created":"2024-01-08","cited_by_count":15,"area":null},{"id":"2411.13476","title":"When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training","created":"2024-11-20","cited_by_count":15,"area":null},{"id":"2506.09997","title":"DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos","created":"2025-06-11","cited_by_count":15,"area":null},{"id":"2203.00854","title":"FastFold: Reducing AlphaFold Training Time from 11 Days to 67 Hours","created":"2022-03-02","cited_by_count":14,"area":null},{"id":"2210.13447","title":"Precision Machine Learning","created":"2022-10-24","cited_by_count":14,"area":null},{"id":"2406.12246","title":"TroL: Traversal of Layers for Large Language and Vision Models","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2410.20650","title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks","created":"2024-10-28","cited_by_count":14,"area":null},{"id":"2510.27527","title":"TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control","created":"2025-10-31","cited_by_count":14,"area":null},{"id":"2405.20271","title":"ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections","created":"2024-05-30","cited_by_count":12,"area":null},{"id":"2405.20835","title":"Outliers and Calibration Sets have Diminishing Effect on Quantization of Modern LLMs","created":"2024-05-31","cited_by_count":12,"area":null},{"id":"2502.12171","title":"GoRA: Gradient-driven Adaptive Low Rank Adaptation","created":"2025-02-13","cited_by_count":12,"area":null},{"id":"2502.15814","title":"Slamming: Training a Speech Language Model on One GPU in a Day","created":"2025-02-19","cited_by_count":12,"area":null},{"id":"2505.15304","title":"Saliency-Aware Quantized Imitation Learning for Efficient Robotic Control","created":"2025-05-21","cited_by_count":12,"area":"vla"},{"id":"2103.14739","title":"Leaky Nets: Recovering Embedded Neural Network Models and Inputs through Simple Power and Timing Side-Channels -- Attacks and Defenses","created":"2021-03-26","cited_by_count":11,"area":null},{"id":"2307.07421","title":"SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding","created":"2023-07-12","cited_by_count":11,"area":null},{"id":"2404.15778","title":"BASS: Batched Attention-optimized Speculative Sampling","created":"2024-04-24","cited_by_count":11,"area":"inference"},{"id":"2505.01043","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2505.20524","title":"Towards Fully FP8 GEMM LLM Training at Scale","created":"2025-05-26","cited_by_count":11,"area":null},{"id":"2305.19167","title":"Reduced Precision Floating-Point Optimization for Deep Neural Network On-Device Learning on MicroControllers","created":"2023-05-30","cited_by_count":10,"area":null},{"id":"2405.03637","title":"Collage: Light-Weight Low-Precision Strategy for LLM Training","created":"2024-05-06","cited_by_count":10,"area":null},{"id":"2502.20566","title":"Stochastic Rounding for LLM Training: Theory and Practice","created":"2025-02-27","cited_by_count":10,"area":null},{"id":"2112.15131","title":"Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2307.15034","title":"Guaranteed Approximation Bounds for Mixed-Precision Neural Operators","created":"2023-07-27","cited_by_count":9,"area":null},{"id":"2312.15696","title":"EcomGPT-CT: Continual Pre-training of E-commerce Large Language Models with Semi-structured Data","created":"2023-12-25","cited_by_count":9,"area":null},{"id":"2405.18710","title":"To FP8 and Back Again: Quantifying Reduced Precision Effects on LLM Training Stability","created":"2024-05-29","cited_by_count":9,"area":null},{"id":"2406.18820","title":"Universal Checkpointing: A Flexible and Efficient Distributed Checkpointing System for Large-Scale DNN Training with Reconfigurable Parallelis","created":"2024-06-27","cited_by_count":9,"area":null},{"id":"2501.06589","title":"Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping","created":"2025-01-11","cited_by_count":9,"area":null},{"id":"2512.23611","title":"Close the Loop: Synthesizing Infinite Tool-Use Data via Multi-Agent Role-Playing","created":"2025-12-29","cited_by_count":9,"area":"agents"},{"id":"2202.06854","title":"Random Laplacian Features for Learning with Hyperbolic Space","created":"2022-02-14","cited_by_count":8,"area":null},{"id":"2603.14360","title":"M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling","created":"2026-03-15","cited_by_count":8,"area":null},{"id":"2403.08845","title":"Bifurcated Attention: Accelerating Massively Parallel Decoding with Shared Prefixes in LLMs","created":"2024-03-13","cited_by_count":7,"area":"inference"},{"id":"2409.16626","title":"Ascend HiFloat8 Format for Deep Learning","created":"2024-09-25","cited_by_count":7,"area":null},{"id":"2411.17000","title":"SatVision-TOA: A Geospatial Foundation Model for Coarse-Resolution All-Sky Remote Sensing Imagery","created":"2024-11-26","cited_by_count":7,"area":null},{"id":"2502.08145","title":"Democratizing AI: Open-source Scalable LLM Training on GPU-based Supercomputers","created":"2025-02-12","cited_by_count":7,"area":null},{"id":"2512.04763","title":"MemLoRA: Distilling Expert Adapters for On-Device Memory Systems","created":"2025-12-04","cited_by_count":7,"area":null},{"id":"2601.08427","title":"Silence the Judge: Reinforcement Learning with Self-Verifier via Latent Geometric Clustering","created":"2026-01-13","cited_by_count":7,"area":"lr"},{"id":"2111.00680","title":"GNNear: Accelerating Full-Batch Training of Graph Neural Networks with Near-Memory Processing","created":"2021-11-01","cited_by_count":6,"area":null},{"id":"2210.12924","title":"OLLA: Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks","created":"2022-10-24","cited_by_count":6,"area":null},{"id":"2303.05295","title":"Dynamic Stashing Quantization for Efficient Transformer Training","created":"2023-03-09","cited_by_count":6,"area":null},{"id":"2311.12315","title":"AcademicGPT: Empowering Academic Research","created":"2023-11-21","cited_by_count":6,"area":null},{"id":"2406.02613","title":"ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2410.00907","title":"Addition is All You Need for Energy-efficient Language Models","created":"2024-10-01","cited_by_count":6,"area":null},{"id":"2503.15465","title":"FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers","created":"2025-03-19","cited_by_count":6,"area":"diffusion"},{"id":"2506.09349","title":"DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations","created":"2025-06-11","cited_by_count":6,"area":null},{"id":"2508.16929","title":"Dimensional Collapse in Transformer Attention Outputs: A Challenge for Sparse Dictionary Learning","created":"2025-08-23","cited_by_count":6,"area":"mechinterp"},{"id":"2606.20128","title":"The Correctness Illusion in LLM-Generated GPU Kernels","created":"2026-06-18","cited_by_count":6,"area":null}],"next_cursor":"100"}