{"total":75,"rows":[{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"id":"2411.12372","title":"RedPajama: an Open Dataset for Training Large Language Models","created":"2024-11-19","cited_by_count":182,"area":null},{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177,"area":null},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2411.13676","title":"Hymba: A Hybrid-head Architecture for Small Language Models","created":"2024-11-20","cited_by_count":99,"area":null},{"id":"2502.05795","title":"The Curse of Depth in Large Language Models","created":"2025-02-09","cited_by_count":62,"area":null},{"id":"2509.14252","title":"LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures","created":"2025-09-11","cited_by_count":38,"area":null},{"id":"2502.11569","title":"Towards Reasoning Ability of Small Language Models","created":"2025-02-17","cited_by_count":29,"area":"lr"},{"id":"2406.09913","title":"OpenECAD: An Efficient Visual Language Model for Editable 3D-CAD Design","created":"2024-06-14","cited_by_count":26,"area":null},{"id":"2503.05804","title":"Holistically Evaluating the Environmental Impact of Creating Language Models","created":"2025-03-03","cited_by_count":26,"area":null},{"id":"2502.15964","title":"Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models","created":"2025-02-21","cited_by_count":20,"area":"lr"},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2505.08137","title":"Large Language Models for Computer-Aided Design: A Survey","created":"2025-05-13","cited_by_count":18,"area":null},{"id":"2405.08707","title":"Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory","created":"2024-05-14","cited_by_count":12,"area":null},{"id":"2404.19296","title":"Octopus v4: Graph of language models","created":"2024-04-30","cited_by_count":11,"area":null},{"id":"2409.12545","title":"Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment","created":"2024-09-19","cited_by_count":11,"area":"distill"},{"id":"2410.08391","title":"KV Prediction for Improved Time to First Token","created":"2024-10-10","cited_by_count":11,"area":"inference"},{"id":"2504.17238","title":"Crisp: Cognitive Restructuring of Negative Thoughts through Multi-turn Supportive Dialogues","created":"2025-04-24","cited_by_count":11,"area":"lr"},{"id":"2506.03101","title":"Beyond Text Compression: Evaluating Tokenizers Across Scales","created":"2025-06-03","cited_by_count":11,"area":null},{"id":"2507.01438","title":"EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices","created":"2025-07-02","cited_by_count":11,"area":"inference"},{"id":"2412.01822","title":"VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models","created":"2024-12-02","cited_by_count":10,"area":"mllm"},{"id":"2601.22575","title":"PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile Scenarios","created":"2026-01-30","cited_by_count":10,"area":"mllm"},{"id":"2411.13055","title":"Hardware Scaling Trends and Diminishing Returns in Large-Scale Distributed Training","created":"2024-11-20","cited_by_count":8,"area":null},{"id":"2502.08142","title":"Bridging the Safety Gap: A Guardrail Pipeline for Trustworthy LLM Inferences","created":"2025-02-12","cited_by_count":8,"area":"safety"},{"id":"2504.01735","title":"AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization","created":"2025-04-02","cited_by_count":8,"area":"mllm"},{"id":"2506.11144","title":"AlignHuman: Improving Motion and Fidelity via Timestep-Segment Preference Optimization for Audio-Driven Human Animation","created":"2025-06-11","cited_by_count":8,"area":"diffusion"},{"id":"2511.23402","title":"Quantized-Tinyllava: a new multimodal foundation model enables efficient split learning","created":"2025-11-28","cited_by_count":8,"area":null},{"id":"2406.11823","title":"On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and Reasoning","created":"2024-06-17","cited_by_count":7,"area":"lr"},{"id":"2410.02749","title":"Training Language Models on Synthetic Edit Sequences Improves Code Synthesis","created":"2024-10-03","cited_by_count":7,"area":null},{"id":"2410.22587","title":"Toxicity of the Commons: Curating Open-Source Pre-Training Data","created":"2024-10-29","cited_by_count":7,"area":null},{"id":"2502.14907","title":"GneissWeb: Preparing High Quality Data for LLMs at Scale","created":"2025-02-19","cited_by_count":7,"area":null},{"id":"2602.22617","title":"Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA","created":"2026-02-26","cited_by_count":7,"area":null},{"id":"2510.15280","title":"Foundation Models for Scientific Discovery: From Paradigm Enhancement to Paradigm Transition","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2405.14277","title":"Improving Language Models Trained on Translated Data with Continual Pre-Training and Dictionary Learning Analysis","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2407.10855","title":"Weighted Grouped Query Attention in Transformers","created":"2024-07-15","cited_by_count":5,"area":null},{"id":"2410.03750","title":"SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models","created":"2024-10-01","cited_by_count":5,"area":null},{"id":"2505.06297","title":"Lossless Compression of Large Language Model-Generated Text via Next-Token Prediction","created":"2025-05-07","cited_by_count":5,"area":"synth"},{"id":"2511.11907","title":"KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference","created":"2025-11-14","cited_by_count":5,"area":"inference"},{"id":"2406.10847","title":"TorchOpera: A Compound AI System for LLM Safety","created":"2024-06-16","cited_by_count":4,"area":"safety"},{"id":"2410.11985","title":"The Fair Language Model Paradox","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2406.14758","title":"Compliance Cards: Automated EU AI Act Compliance Analyses amidst a Complex AI Supply Chain","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2508.11255","title":"FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation","created":"2025-08-15","cited_by_count":3,"area":"alignment"},{"id":"2605.23857","title":"Strong Teacher Not Needed? On Distillation in LLM Pretraining","created":"2026-05-22","cited_by_count":3,"area":"distill"},{"id":"2410.09692","title":"ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flaws","created":"2024-10-13","cited_by_count":2,"area":null},{"id":"2501.05465","title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)","created":"2025-01-03","cited_by_count":2,"area":null},{"id":"2503.06029","title":"SmartBench: Is Your LLM Truly a Good Chinese Smartphone Assistant?","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2505.21598","title":"Rethinking Data Mixture for Large Language Models: A Comprehensive Survey and New Perspectives","created":"2025-05-27","cited_by_count":2,"area":"lr"},{"id":"2506.11402","title":"LoRA Users Beware: A Few Spurious Tokens Can Manipulate Your Finetuned Model","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2509.06518","title":"Crown, Frame, Reverse: Layer-Wise Scaling Variants for LLM Pre-Training","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2604.07963","title":"Rethinking Data Mixing from the Perspective of Large Language Models","created":"2026-04-09","cited_by_count":2,"area":"lr"},{"id":"2407.04542","title":"Rethinking Image Compression on the Web with Generative AI","created":"2024-07-05","cited_by_count":1,"area":null},{"id":"2502.01220","title":"Factual Knowledge in Language Models: Robustness and Anomalies under Simple Temporal Context Variations","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2502.16701","title":"Beyond Release: Access Considerations for Generative AI Systems","created":"2025-02-23","cited_by_count":1,"area":null},{"id":"2503.07216","title":"FedRand: Enhancing Privacy in Federated Learning with Randomized LoRA Subparameter Updates","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2504.06323","title":"Mosaic: Composite Projection Pruning for Resource-efficient LLMs","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2504.07965","title":"Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments","created":"2025-04-10","cited_by_count":1,"area":"alignment"},{"id":"2506.13180","title":"Dynamic Acoustic Model Architecture Optimization in Training for ASR","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2606.18246","title":"Variable-Width Transformers","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2609.14743","title":"Quantifying the Generation Modality Gap in Speech-Text Language Models","created":"2026-09-13","cited_by_count":1,"area":null},{"id":"2406.11410","title":"HARE: HumAn pRiors, a key to small language model Efficiency","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2410.07062","title":"TinyEmo: Scaling down Emotional Reasoning via Metric Projection","created":"2024-10-09","cited_by_count":0,"area":"lr"},{"id":"2502.20975","title":"Set-Theoretic Compositionality of Sentence Embeddings","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2505.14992","title":"Effective and Efficient Schema-aware Information Extraction Using On-Device Large Language Models","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2505.17169","title":"Next Token Perception Score: Analytical Assessment of your LLM Perception Skills","created":"2025-05-22","cited_by_count":0,"area":"mechinterp"},{"id":"2506.11120","title":"SDMPrune: Self-Distillation MLP Pruning for Efficient Large Language Models","created":"2025-06-10","cited_by_count":0,"area":"distill"},{"id":"2508.01540","title":"MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning","created":"2025-08-03","cited_by_count":0,"area":"mllm"},{"id":"2509.01232","title":"FantasyHSI: Video-Generation-Centric 4D Human Synthesis In Any Scene through A Graph-based Multi-Agent Framework","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2509.19341","title":"Fine-Grained AI Model Caching and Downloading With Coordinated Multipoint Broadcasting in Multi-Cell Edge Networks","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.21192","title":"GEP: A GCG-Based method for extracting personally identifiable information from chatbots built on small language models","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2602.11543","title":"Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm","created":"2026-02-12","cited_by_count":0,"area":"moe"},{"id":"2605.17653","title":"LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2607.28639","title":"The Asymmetric Effects of Knowledge Distillation on Bias in Small Language Models","created":"2026-05-19","cited_by_count":0,"area":"distill"},{"id":"2608.26650","title":"Meta-Learning Where to Allocate Experts: Task-Conditioned Layer-Wise Compression for MoEs","created":"2026-08-27","cited_by_count":0,"area":"moe"},{"id":"2609.14643","title":"BigMoMo: Efficient Inference of Large-Scale MoE with Speculative Decoding on Mobile Devices","created":"2026-09-13","cited_by_count":0,"area":"moe"}],"next_cursor":null}