{"total":130,"rows":[{"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":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209,"area":"mllm"},{"id":"2412.11948","title":"OpenReviewer: A Specialized Large Language Model for Generating Critical Scientific Paper Reviews","created":"2024-12-16","cited_by_count":65,"area":null},{"id":"2603.04379","title":"Helios: Real Real-Time Long Video Generation Model","created":"2026-03-04","cited_by_count":65,"area":null},{"id":"2508.15763","title":"Intern-S1: A Scientific Multimodal Foundation Model","created":"2025-08-21","cited_by_count":53,"area":"moe"},{"id":"2504.12285","title":"BitNet b1.58 2B4T Technical Report","created":"2025-04-16","cited_by_count":38,"area":null},{"id":"2502.17407","title":"Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning","created":"2025-02-24","cited_by_count":37,"area":"lr"},{"id":"2505.13949","title":"FlashThink: An Early Exit Method For Efficient Reasoning","created":"2025-05-20","cited_by_count":28,"area":"lr"},{"id":"2502.01567","title":"Latent Thought Models with Variational Bayes Inference-Time Computation","created":"2025-02-03","cited_by_count":25,"area":"lr"},{"id":"2505.21925","title":"RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination","created":"2025-05-28","cited_by_count":23,"area":null},{"id":"2504.05747","title":"SEA-LION: Southeast Asian Languages in One Network","created":"2025-04-08","cited_by_count":22,"area":null},{"id":"2502.17421","title":"LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification","created":"2025-02-24","cited_by_count":21,"area":"agents"},{"id":"2502.09604","title":"SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models","created":"2025-02-13","cited_by_count":20,"area":"alignment"},{"id":"2508.02317","title":"VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo","created":"2025-08-04","cited_by_count":20,"area":"moe"},{"id":"2605.16826","title":"Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation","created":"2026-05-16","cited_by_count":20,"area":"offlinerl"},{"id":"2507.14675","title":"Docopilot: Improving Multimodal Models for Document-Level Understanding","created":"2025-07-19","cited_by_count":19,"area":"mllm"},{"id":"2510.14969","title":"LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training","created":"2025-10-16","cited_by_count":18,"area":null},{"id":"2410.18027","title":"Cross-lingual Transfer of Reward Models in Multilingual Alignment","created":"2024-10-23","cited_by_count":17,"area":"alignment"},{"id":"2504.07053","title":"TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","created":"2025-04-09","cited_by_count":16,"area":null},{"id":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2603.12938","title":"Thinking in Streaming Video","created":"2026-03-13","cited_by_count":16,"area":null},{"id":"2505.01583","title":"TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action","created":"2025-05-02","cited_by_count":14,"area":"lr"},{"id":"2505.13772","title":"Krikri: Advancing Open Large Language Models for Greek","created":"2025-05-19","cited_by_count":14,"area":null},{"id":"2601.02204","title":"NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation","created":"2026-01-05","cited_by_count":14,"area":null},{"id":"2411.07854","title":"Tucano: Advancing Neural Text Generation for Portuguese","created":"2024-11-12","cited_by_count":13,"area":null},{"id":"2502.12171","title":"GoRA: Gradient-driven Adaptive Low Rank Adaptation","created":"2025-02-13","cited_by_count":12,"area":null},{"id":"2601.06395","title":"AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages","created":"2026-01-10","cited_by_count":12,"area":null},{"id":"2504.11919","title":"Rethinking the Generation of High-Quality CoT Data from the Perspective of LLM-Adaptive Question Difficulty Grading","created":"2025-04-16","cited_by_count":11,"area":"lr"},{"id":"2509.21320","title":"SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines","created":"2025-09-25","cited_by_count":11,"area":"lr"},{"id":"2601.15727","title":"Towards Automated Kernel Generation in the Era of LLMs","created":"2026-01-22","cited_by_count":11,"area":"agents"},{"id":"2602.17004","title":"Arcee Trinity Large Technical Report","created":"2026-02-19","cited_by_count":11,"area":"moe"},{"id":"2504.12463","title":"Dense Backpropagation Improves Training for Sparse Mixture-of-Experts","created":"2025-04-16","cited_by_count":10,"area":"moe"},{"id":"2510.04230","title":"Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought","created":"2025-10-05","cited_by_count":10,"area":"lr"},{"id":"2411.16365","title":"Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines","created":"2024-11-25","cited_by_count":9,"area":"rag"},{"id":"2502.09056","title":"Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe","created":"2025-02-13","cited_by_count":9,"area":"lr"},{"id":"2506.02267","title":"TransAct V2: Lifelong User Action Sequence Modeling on Pinterest Recommendation","created":"2025-06-02","cited_by_count":9,"area":null},{"id":"2510.02386","title":"On The Fragility of Benchmark Contamination Detection in Reasoning Models","created":"2025-09-30","cited_by_count":9,"area":"lr"},{"id":"2510.23538","title":"JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence","created":"2025-10-27","cited_by_count":9,"area":null},{"id":"2510.25771","title":"Gaperon: A Peppered English-French Generative Language Model Suite","created":"2025-10-29","cited_by_count":9,"area":null},{"id":"2602.05879","title":"EuroLLM-22B: Technical Report","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2412.17743","title":"YuLan-Mini: An Open Data-efficient Language Model","created":"2024-12-23","cited_by_count":7,"area":null},{"id":"2505.17315","title":"Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2508.03709","title":"MD-LLM-1: A Large Language Model for Molecular Dynamics","created":"2025-07-21","cited_by_count":7,"area":null},{"id":"2410.23261","title":"$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2509.10105","title":"VARCO-VISION-2.0 Technical Report","created":"2025-09-12","cited_by_count":6,"area":"mllm"},{"id":"2510.05132","title":"Training Large Language Models To Reason In Parallel With Global Forking Tokens","created":"2025-10-01","cited_by_count":6,"area":"lr"},{"id":"2511.20102","title":"SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space","created":"2025-11-25","cited_by_count":6,"area":null},{"id":"2512.03383","title":"UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs","created":"2025-12-03","cited_by_count":6,"area":null},{"id":"2608.26105","title":"VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning","created":"2026-08-26","cited_by_count":6,"area":"lr"},{"id":"2503.13661","title":"Pensez: Less Data, Better Reasoning -- Rethinking French LLM","created":"2025-03-17","cited_by_count":5,"area":"lr"},{"id":"2505.19293","title":"100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability?","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2605.01925","title":"CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Models","created":"2026-05-03","cited_by_count":5,"area":"mllm"},{"id":"2605.15871","title":"Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design","created":"2026-05-15","cited_by_count":5,"area":"agents"},{"id":"2605.19269","title":"CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs","created":"2026-05-19","cited_by_count":5,"area":null},{"id":"2502.15132","title":"CoT-ICL Lab: A Synthetic Framework for Studying Chain-of-Thought Learning from In-Context Demonstrations","created":"2025-02-21","cited_by_count":4,"area":"lr"},{"id":"2505.14305","title":"JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2601.22362","title":"Understanding Efficiency: Quantization, Batching, and Serving Strategies in LLM Energy Use","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2602.18700","title":"Watermarking LLM Agent Trajectories","created":"2026-02-21","cited_by_count":4,"area":"agents"},{"id":"2604.03582","title":"Simple yet Effective: Low-Rank Spatial Attention for Neural Operators","created":"2026-04-04","cited_by_count":4,"area":null},{"id":"2502.09042","title":"Typhoon T1: An Open Thai Reasoning Model","created":"2025-02-13","cited_by_count":3,"area":"lr"},{"id":"2503.22517","title":"Exploiting Mixture-of-Experts Redundancy Unlocks Multimodal Generative Abilities","created":"2025-03-28","cited_by_count":3,"area":"moe"},{"id":"2505.10292","title":"StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation","created":"2025-05-15","cited_by_count":3,"area":"lr"},{"id":"2505.24691","title":"Speech-to-Text Translation with Phoneme-Augmented CoT: Enhancing Cross-Lingual Transfer in Low-Resource Scenarios","created":"2025-05-30","cited_by_count":3,"area":"lr"},{"id":"2506.00482","title":"Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHub","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2506.13996","title":"Arctic Long Sequence Training: Scalable And Efficient Training For Multi-Million Token Sequences","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2510.00206","title":"LoRAFusion: Efficient LoRA Fine-Tuning for LLMs","created":"2025-09-30","cited_by_count":3,"area":null},{"id":"2510.12210","title":"DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2511.21272","title":"Co-Training Vision Language Models for Remote Sensing Multi-task Learning","created":"2025-11-26","cited_by_count":3,"area":"mllm"},{"id":"2601.13806","title":"Knowledge Graph-Assisted LLM Post-Training for Enhanced Legal Reasoning","created":"2026-01-20","cited_by_count":3,"area":"lr"},{"id":"2603.15854","title":"FlashSampling: Fast and Memory-Efficient Exact Sampling","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2606.13578","title":"LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories","created":"2026-06-11","cited_by_count":3,"area":"vla"},{"id":"2504.05638","title":"TAGC: Optimizing Gradient Communication in Distributed Transformer Training","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2505.16968","title":"CASS: Nvidia to AMD Transpilation with Data, Models, and Benchmark","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2505.22156","title":"InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2505.23117","title":"Decom-Renorm-Merge: Model Merging on the Right Space Improves Multitasking","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2511.11313","title":"DocSLM: A Small Vision-Language Model for Long Multimodal Document Understanding","created":"2025-11-14","cited_by_count":2,"area":"lr"},{"id":"2511.12207","title":"Mixture of States: Routing Token-Level Dynamics for Multimodal Generation","created":"2025-11-15","cited_by_count":2,"area":"diffusion"},{"id":"2512.04142","title":"From FLOPs to Footprints: The Resource Cost of Artificial Intelligence","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2512.15306","title":"LLMQ: Efficient Lower-Precision Pretraining for Consumer GPUs","created":"2025-12-17","cited_by_count":2,"area":null},{"id":"2606.04847","title":"MusaCoder: Native GPU Kernel Generation with Full-Stack Training on Moore Threads GPU","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2606.22932","title":"FORGE: Fused On-Register Gradient Elimination for Memory-Efficient LLM Training","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2608.03796","title":"Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss","created":"2026-08-04","cited_by_count":2,"area":"distill"},{"id":"2608.12004","title":"RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2505.12260","title":"LightRetriever: A LLM-based Text Retrieval Architecture with Extremely Faster Query Inference","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2506.00189","title":"Control-R: Towards controllable test-time scaling","created":"2025-05-30","cited_by_count":1,"area":"lr"},{"id":"2506.20686","title":"MegaFold: Efficient Training of Next-Generation 3D Attention Protein Models on Cross-Platform GPUs","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2509.06326","title":"AttestLLM: Efficient Attestation Framework for Billion-scale On-device LLMs","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2509.12266","title":"Genome-Factory: A Library for Tuning, Deploying, and Interpreting Genomic Foundation Models","created":"2025-09-13","cited_by_count":1,"area":null},{"id":"2510.03115","title":"Listening or Reading? Evaluating Speech Awareness in Chain-of-Thought Speech-to-Text Translation","created":"2025-10-03","cited_by_count":1,"area":"lr"},{"id":"2512.07846","title":"MixLM: High-Throughput and Effective LLM Ranking via Text-Embedding Mix-Interaction","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2512.11463","title":"Motif-2-12.7B-Reasoning: A Practitioner's Guide to RL Training Recipes","created":"2025-12-11","cited_by_count":1,"area":"lr"},{"id":"2602.07309","title":"Semantic Search At LinkedIn","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2602.21196","title":"Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.22276","title":"Scaling DoRA: High-Rank Adaptation via Factored Norms and Fused Kernels","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2604.00001","title":"Filter-then-Weight: Online Data Selection and Reweighting for LLM Fine-Tuning","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2604.02340","title":"Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models","created":"2026-02-04","cited_by_count":1,"area":"diffusion"},{"id":"2605.14790","title":"Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2607.20145","title":"SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD","created":"2026-07-22","cited_by_count":1,"area":"moe"},{"id":"2608.08469","title":"Aero Realtime: Fully Aligned Input-Output Streams for Low-Latency Streaming Multimodal Generation","created":"2026-08-09","cited_by_count":1,"area":"inference"},{"id":"2503.17963","title":"Won: Establishing Best Practices for Korean Financial NLP","created":"2025-03-23","cited_by_count":0,"area":null}],"next_cursor":"100"}