{"total":100,"rows":[{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719,"area":null},{"id":"2401.15077","title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","created":"2024-01-26","cited_by_count":578,"area":"lr"},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326,"area":"mllm"},{"id":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173,"area":"mllm"},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2402.05109","title":"Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding","created":"2024-02-07","cited_by_count":117,"area":"inference"},{"id":"2408.02479","title":"From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future","created":"2024-08-05","cited_by_count":86,"area":"agents"},{"id":"2402.04833","title":"Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning","created":"2024-02-07","cited_by_count":85,"area":"alignment"},{"id":"2402.05119","title":"A Closer Look at the Limitations of Instruction Tuning","created":"2024-02-03","cited_by_count":77,"area":null},{"id":"2408.16673","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":70,"area":null},{"id":"2406.10209","title":"Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs","created":"2024-06-14","cited_by_count":50,"area":null},{"id":"2405.14394","title":"Instruction Tuning With Loss Over Instructions","created":"2024-05-23","cited_by_count":40,"area":null},{"id":"2404.01266","title":"IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations","created":"2024-04-01","cited_by_count":38,"area":null},{"id":"2501.09929","title":"Interpretable Steering of Large Language Models with Feature Guided Activation Additions","created":"2025-01-17","cited_by_count":35,"area":"mechinterp"},{"id":"2408.11857","title":"Hermes 3 Technical Report","created":"2024-08-15","cited_by_count":34,"area":null},{"id":"2404.08680","title":"Automating Research Synthesis with Domain-Specific Large Language Model Fine-Tuning","created":"2024-04-08","cited_by_count":31,"area":null},{"id":"2404.01231","title":"Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models","created":"2024-04-01","cited_by_count":30,"area":null},{"id":"2504.15266","title":"Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction","created":"2025-04-21","cited_by_count":29,"area":null},{"id":"2410.03730","title":"Teuken-7B-Base & Teuken-7B-Instruct: Towards European LLMs","created":"2024-09-30","cited_by_count":22,"area":null},{"id":"2402.10908","title":"LLM-Assisted Crisis Management: Building Advanced LLM Platforms for Effective Emergency Response and Public Collaboration","created":"2024-01-12","cited_by_count":21,"area":null},{"id":"2403.02178","title":"Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models","created":"2024-03-04","cited_by_count":20,"area":"lr"},{"id":"2405.01886","title":"Aloe: A Family of Fine-tuned Open Healthcare LLMs","created":"2024-05-03","cited_by_count":20,"area":"safety"},{"id":"2505.07849","title":"SweRank: Software Issue Localization with Code Ranking","created":"2025-05-07","cited_by_count":20,"area":null},{"id":"2403.01342","title":"LM4OPT: Unveiling the Potential of Large Language Models in Formulating Mathematical Optimization Problems","created":"2024-03-02","cited_by_count":18,"area":null},{"id":"2407.15851","title":"A Survey on Trustworthiness in Foundation Models for Medical Image Analysis","created":"2024-07-03","cited_by_count":17,"area":null},{"id":"2409.12136","title":"GRIN: GRadient-INformed MoE","created":"2024-09-18","cited_by_count":17,"area":"moe"},{"id":"2401.03804","title":"TeleChat Technical Report","created":"2024-01-08","cited_by_count":15,"area":null},{"id":"2501.18532","title":"Differentially Private Steering for Large Language Model Alignment","created":"2025-01-30","cited_by_count":15,"area":"alignment"},{"id":"2502.18448","title":"Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing","created":"2025-02-25","cited_by_count":13,"area":null},{"id":"2506.01317","title":"T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning","created":"2025-06-02","cited_by_count":13,"area":null},{"id":"2502.14050","title":"Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder","created":"2025-02-19","cited_by_count":12,"area":"mechinterp"},{"id":"2402.11176","title":"KnowTuning: Knowledge-aware Fine-tuning for Large Language Models","created":"2024-02-17","cited_by_count":11,"area":null},{"id":"2401.03741","title":"Enhanced Automated Code Vulnerability Repair using Large Language Models","created":"2024-01-08","cited_by_count":10,"area":null},{"id":"2409.08234","title":"LLM Honeypot: Leveraging Large Language Models as Advanced Interactive Honeypot Systems","created":"2024-09-12","cited_by_count":10,"area":null},{"id":"2405.20494","title":"Slight Corruption in Pre-training Data Makes Better Diffusion Models","created":"2024-05-30","cited_by_count":9,"area":"diffusion"},{"id":"2505.13787","title":"Preference Learning with Lie Detectors can Induce Honesty or Evasion","created":"2025-05-20","cited_by_count":9,"area":"alignment"},{"id":"2404.09445","title":"Exploring Text-to-Motion Generation with Human Preference","created":"2024-04-15","cited_by_count":8,"area":null},{"id":"2407.03495","title":"Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations","created":"2024-07-03","cited_by_count":8,"area":null},{"id":"2401.15496","title":"Baichuan2-Sum: Instruction Finetune Baichuan2-7B Model for Dialogue Summarization","created":"2024-01-27","cited_by_count":7,"area":null},{"id":"2403.06832","title":"Noise-powered Multi-modal Knowledge Graph Representation Framework","created":"2024-03-11","cited_by_count":7,"area":null},{"id":"2410.14655","title":"Bridging the Training-Inference Gap in LLMs by Leveraging Self-Generated Tokens","created":"2024-10-18","cited_by_count":7,"area":"synth"},{"id":"2412.06619","title":"Copyright-Protected Language Generation via Adaptive Model Fusion","created":"2024-12-09","cited_by_count":7,"area":null},{"id":"2602.15322","title":"On Surprising Effectiveness of Masking Updates in Adaptive Optimizers","created":"2026-02-17","cited_by_count":7,"area":null},{"id":"2407.18897","title":"Small Molecule Optimization with Large Language Models","created":"2024-07-26","cited_by_count":6,"area":null},{"id":"2401.07544","title":"See the Unseen: Better Context-Consistent Knowledge-Editing by Noises","created":"2024-01-15","cited_by_count":5,"area":null},{"id":"2406.02110","title":"UniOQA: A Unified Framework for Knowledge Graph Question Answering with Large Language Models","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2407.11654","title":"R-SFLLM: Jamming Resilient Framework for Split Federated Learning with Large Language Models","created":"2024-07-16","cited_by_count":5,"area":null},{"id":"2408.08261","title":"mhGPT: A Lightweight Generative Pre-Trained Transformer for Mental Health Text Analysis","created":"2024-08-15","cited_by_count":5,"area":null},{"id":"2503.13661","title":"Pensez: Less Data, Better Reasoning -- Rethinking French LLM","created":"2025-03-17","cited_by_count":5,"area":"lr"},{"id":"2602.08222","title":"Weak-Driven Learning: How Weak Agents make Strong Agents Stronger","created":"2026-02-09","cited_by_count":5,"area":"agents"},{"id":"2402.09759","title":"Efficient Language Adaptive Pre-training: Extending State-of-the-Art Large Language Models for Polish","created":"2024-02-15","cited_by_count":4,"area":null},{"id":"2407.20105","title":"Strong Copyright Protection for Language Models via Adaptive Model Fusion","created":"2024-07-29","cited_by_count":4,"area":null},{"id":"2411.05508","title":"An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking","created":"2024-11-08","cited_by_count":4,"area":null},{"id":"2411.09539","title":"Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide","created":"2024-11-14","cited_by_count":4,"area":null},{"id":"2510.06627","title":"POME: Post Optimization Model Edit via Muon-style Projection","created":"2025-10-08","cited_by_count":4,"area":null},{"id":"2410.05248","title":"SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2411.00686","title":"Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2502.02007","title":"Reasoning Bias of Next Token Prediction Training","created":"2025-02-04","cited_by_count":3,"area":"lr"},{"id":"2511.13052","title":"Learning from the Undesirable: Robust Adaptation of Language Models without Forgetting","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2605.11936","title":"From Noise to Diversity: Random Embedding Injection in LLM Reasoning","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2505.10845","title":"Ready2Unlearn: A Learning-Time Approach for Preparing Models with Future Unlearning Readiness","created":"2025-05-16","cited_by_count":2,"area":"safety"},{"id":"2505.23868","title":"Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE","created":"2025-05-29","cited_by_count":2,"area":"moe"},{"id":"2508.04337","title":"Modelling and Classifying the Components of a Literature Review","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2509.03972","title":"Expanding Foundational Language Capabilities in Open-Source LLMs through a Korean Case Study","created":"2025-09-04","cited_by_count":2,"area":null},{"id":"2602.00217","title":"Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2401.10580","title":"PHOENIX: Open-Source Language Adaption for Direct Preference Optimization","created":"2024-01-19","cited_by_count":1,"area":"alignment"},{"id":"2407.18423","title":"HDL-GPT: High-Quality HDL is All You Need","created":"2024-07-25","cited_by_count":1,"area":null},{"id":"2502.16274","title":"Fine-Tuning Qwen 2.5 3B for Realistic Movie Dialogue Generation","created":"2025-02-22","cited_by_count":1,"area":null},{"id":"2504.03302","title":"Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2506.10030","title":"Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment","created":"2025-06-10","cited_by_count":1,"area":"rag"},{"id":"2507.16922","title":"A Unifying Scheme for Extractive Content Selection Tasks","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2507.19102","title":"Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generation","created":"2025-07-25","cited_by_count":1,"area":"rag"},{"id":"2508.20381","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2510.11372","title":"Early Detection and Reduction of Memorisation for Domain Adaptation and Instruction Tuning","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2510.22694","title":"Windsock is Dancing: Adaptive Multimodal Retrieval-Augmented Generation","created":"2025-10-26","cited_by_count":1,"area":"mllm"},{"id":"2602.01838","title":"AXE: Low-Cost Cross-Domain Web Structured Information Extraction","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.09066","title":"Spectral Disentanglement and Enhancement: A Dual-domain Contrastive Framework for Representation Learning","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2606.10392","title":"Instruction Finetuning DeepSeek-R1-8B Model Using LoRA and NEFTune","created":"2026-06-09","cited_by_count":1,"area":"lr"},{"id":"2607.23335","title":"The Gate Always Closes: On Injecting Auxiliary Signals into Frozen Vision-Language Models","created":"2026-07-25","cited_by_count":1,"area":"mllm"},{"id":"2607.25091","title":"Towards Robust Reinforcement Learning for Small-Scale Language Model Agents","created":"2026-07-27","cited_by_count":1,"area":"agents"},{"id":"2403.10658","title":"InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning","created":"2024-03-15","cited_by_count":0,"area":null},{"id":"2408.10841","title":"DELIA: Diversity-Enhanced Learning for Instruction Adaptation in Large Language Models","created":"2024-08-19","cited_by_count":0,"area":null},{"id":"2410.00004","title":"Retro-li: Small-Scale Retrieval Augmented Generation Supporting Noisy Similarity Searches and Domain Shift Generalization","created":"2024-09-12","cited_by_count":0,"area":"rag"},{"id":"2410.06348","title":"Harnessing the Power of Noise: A Survey of Techniques and Applications","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2410.19193","title":"Enriching GNNs with Text Contextual Representations for Detecting Disinformation Campaigns on Social Media","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2412.16423","title":"Technical Report: Small Language Model for Japanese Clinical and Medicine","created":"2024-12-21","cited_by_count":0,"area":null},{"id":"2503.08144","title":"Bring Remote Sensing Object Detect Into Nature Language Model: Using SFT Method","created":"2025-03-11","cited_by_count":0,"area":"mllm"},{"id":"2507.03673","title":"TACOS: Open Tagging and Comparative Scoring for Instruction Fine-Tuning Data Selection","created":"2025-07-04","cited_by_count":0,"area":"alignment"},{"id":"2511.20997","title":"FANoise: Singular Value-Adaptive Noise Modulation for Robust Multimodal Representation Learning","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2601.01062","title":"SPoRC-VIST: A Benchmark for Evaluating Generative Natural Narrative in Vision-Language Models","created":"2026-01-03","cited_by_count":0,"area":"mllm"},{"id":"2604.23665","title":"HAC: Parameter-Efficient Hyperbolic Adaptation of CLIP for Zero-Shot VQA","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2605.13284","title":"Learning Perturbations to Extrapolate Your LLM","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.22185","title":"Enhancing Multimodal Large Language Models for Safety-Critical Driving Video Analysis","created":"2026-05-21","cited_by_count":0,"area":"mllm"},{"id":"2605.23171","title":"Understanding and Improving Noisy Embedding Techniques in Instruction Finetuning","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2606.29366","title":"Solver-Verified Formulation Generation and Selection for Multi-Warehouse Inventory Allocation Using Large Language Models","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2608.02939","title":"Federated generative event models for tokenized electronic health records","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.10292","title":"Isotropic Embedding Perturbations for Robust Vision Language Encoders","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.34064","title":"Learning Perturbation Robust Policies for LLM Agents with Stable Optimization","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.17189","title":"Soft Teacher Forcing","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}