{"total":60,"rows":[{"id":"2508.14444","title":"NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model","created":"2025-08-20","cited_by_count":108,"area":"lr"},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104,"area":"lr"},{"id":"2505.11475","title":"HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages","created":"2025-05-16","cited_by_count":75,"area":"alignment"},{"id":"2507.09075","title":"OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique","created":"2025-07-11","cited_by_count":25,"area":"lr"},{"id":"2604.08302","title":"DMax: Aggressive Parallel Decoding for dLLMs","created":"2026-04-09","cited_by_count":18,"area":"diffusion"},{"id":"2512.14681","title":"Fast and Accurate Causal Parallel Decoding using Jacobi Forcing","created":"2025-12-16","cited_by_count":13,"area":"inference"},{"id":"2605.07711","title":"SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation","created":"2026-05-08","cited_by_count":12,"area":"distill"},{"id":"2603.19329","title":"Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification","created":"2026-03-18","cited_by_count":11,"area":null},{"id":"2602.10314","title":"Stop Training for the Worst: Progressive Unmasking Accelerates Masked Diffusion Training","created":"2026-02-10","cited_by_count":10,"area":"diffusion"},{"id":"2512.15176","title":"DEER: Draft with Diffusion, Verify with Autoregressive Models","created":"2025-12-17","cited_by_count":9,"area":"lr"},{"id":"2505.16056","title":"Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models","created":"2025-05-21","cited_by_count":8,"area":"moe"},{"id":"2601.02236","title":"CD4LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models","created":"2026-01-05","cited_by_count":8,"area":"diffusion"},{"id":"2602.07729","title":"Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs","created":"2026-02-07","cited_by_count":7,"area":null},{"id":"2506.07452","title":"When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment","created":"2025-06-09","cited_by_count":6,"area":"safety"},{"id":"2601.15220","title":"Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models","created":"2026-01-21","cited_by_count":6,"area":null},{"id":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","cited_by_count":6,"area":"synth"},{"id":"2602.01469","title":"P-EAGLE: Parallel-Drafting EAGLE with Scalable Training","created":"2026-02-01","cited_by_count":6,"area":"lr"},{"id":"2507.06968","title":"Scaling Towards the Information Boundary of Instruction Sets: The Infinity Instruct Subject Technical Report","created":"2025-07-09","cited_by_count":5,"area":null},{"id":"2602.17684","title":"CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models","created":"2026-02-04","cited_by_count":5,"area":"alignment"},{"id":"2608.01078","title":"Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization","created":"2026-08-02","cited_by_count":5,"area":"lr"},{"id":"2510.23891","title":"PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs","created":"2025-10-27","cited_by_count":4,"area":"safety"},{"id":"2602.09003","title":"Data Science and Technology Towards AGI Part I: Tiered Data Management","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2607.19223","title":"AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters","created":"2026-07-21","cited_by_count":4,"area":"inference"},{"id":"2607.25852","title":"AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding","created":"2026-07-28","cited_by_count":4,"area":"inference"},{"id":"2510.15306","title":"WebGen-V Bench: Structured Representation for Enhancing Visual Design in LLM-based Web Generation and Evaluation","created":"2025-10-17","cited_by_count":3,"area":null},{"id":"2602.08813","title":"Robust Policy Optimization to Prevent Catastrophic Forgetting","created":"2026-02-09","cited_by_count":3,"area":"alignment"},{"id":"2603.03031","title":"Step-Level Sparse Autoencoder for Reasoning Process Interpretation","created":"2026-03-03","cited_by_count":3,"area":"lr"},{"id":"2603.12248","title":"Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models","created":"2026-03-12","cited_by_count":3,"area":null},{"id":"2604.01622","title":"Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models","created":"2026-04-02","cited_by_count":3,"area":"diffusion"},{"id":"2605.30334","title":"Demystifying Data Organization for Enhanced LLM Training","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2604.00824","title":"Yet Even Less Is Even Better For Agentic, Reasoning, and Coding LLMs","created":"2026-04-01","cited_by_count":2,"area":"lr"},{"id":"2606.27617","title":"Masked Language Flow Models","created":"2026-06-26","cited_by_count":2,"area":"diffusion"},{"id":"2607.22039","title":"Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs","created":"2026-07-24","cited_by_count":2,"area":null},{"id":"2608.25756","title":"TailSFT: Filtered Fine-Tuning Improves Post-Training Performance","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2508.09537","title":"From Context to Intent: Reasoning-Guided Function-Level Code Completion","created":"2025-08-13","cited_by_count":1,"area":"lr"},{"id":"2601.00575","title":"InfoSynth: Information-Guided Benchmark Synthesis for LLMs","created":"2026-01-02","cited_by_count":1,"area":null},{"id":"2601.06428","title":"BackPlay: Head-Only Look-Back Self-Correction for Diffusion Language Models","created":"2026-01-10","cited_by_count":1,"area":"diffusion"},{"id":"2602.16488","title":"Learning to Learn from Language Feedback with Social Meta-Learning","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2603.29292","title":"Self-Improving Code Generation via Semantic Entropy and Behavioral Consensus","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"id":"2606.13867","title":"Muon$^p$: Muon with Fractional Spectral Powers","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.18286","title":"CODEBLOCK: Learning to Supervise Code at the Right Granularity","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.18327","title":"Self-CTRL: Self-Consistency Training with Reinforcement Learning","created":"2026-06-16","cited_by_count":1,"area":"lr"},{"id":"2607.26504","title":"From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models","created":"2026-07-29","cited_by_count":1,"area":"diffusion"},{"id":"2608.13925","title":"CForce: Boosting Parallel Decoding for dLLMs via Consistency Forcing","created":"2026-08-14","cited_by_count":1,"area":"inference"},{"id":"2609.29102","title":"ELF-REG: Scaling Continuous Diffusion Language Models to Reasoning Tasks","created":"2026-09-24","cited_by_count":1,"area":"lr"},{"id":"2609.35694","title":"Reasoning with Continuous Latent Diffusion","created":"2026-09-28","cited_by_count":1,"area":"diffusion"},{"id":"2512.20328","title":"Toward Explaining Large Language Models in Software Engineering Tasks","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2512.23747","title":"State-of-the-art Small Language Coder Model: Mify-Coder","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2601.09398","title":"Ability Transfer and Recovery via Modularized Parameters Localization","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2604.17010","title":"Improving LLM Code Reasoning via Semantic Equivalence Self-Play with Formal Verification","created":"2026-04-18","cited_by_count":0,"area":"lr"},{"id":"2605.21180","title":"Domain-Adaptable Reinforcement Learning for Code Generation with Dense Rewards","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.27971","title":"Semantic Flow Regularization: Teaching LLMs to Generate Diverse Yet Coherent Responses","created":"2026-05-27","cited_by_count":0,"area":"diffusion"},{"id":"2606.11817","title":"Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code","created":"2026-06-10","cited_by_count":0,"area":"safety"},{"id":"2606.28998","title":"Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation","created":"2026-06-27","cited_by_count":0,"area":"alignment"},{"id":"2607.11940","title":"CARE-LoRA: Compressed Activation REconstruction for Memory-Efficient LoRA","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2609.16372","title":"Register Tokens for Bounded-State Reasoning in Diffusion Language Models","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.38066","title":"Alpha Diffusion Language Models: Factorization Alone Is Not the Problem","created":"2026-09-29","cited_by_count":0,"area":"diffusion"},{"id":"2610.11548","title":"Conditional Transfer from Controlled Pretraining Mixtures to Code","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.14437","title":"From Transfer Probes to Expert Grouping: Evidence from LoRA Post-Training","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.14745","title":"SAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}