{"total":21,"rows":[{"id":"2408.06621","title":"Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs","created":"2024-08-13","cited_by_count":36,"area":"lr"},{"id":"2506.15674","title":"Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers","created":"2025-06-18","cited_by_count":28,"area":"lr"},{"id":"2503.04543","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","created":"2025-03-06","cited_by_count":16,"area":"lr"},{"id":"2510.03255","title":"SciTS: Scientific Time Series Understanding and Generation with LLMs","created":"2025-09-26","cited_by_count":15,"area":"lr"},{"id":"2506.00772","title":"LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning","created":"2025-06-01","cited_by_count":12,"area":"lr"},{"id":"2412.00151","title":"DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness","created":"2024-11-29","cited_by_count":8,"area":"lr"},{"id":"2501.07890","title":"GRAPHMOE: Amplifying Cognitive Depth of Mixture-of-Experts Network via Introducing Self-Rethinking Mechanism","created":"2025-01-14","cited_by_count":7,"area":"lr"},{"id":"2507.04453","title":"ESSA: Evolutionary Strategies for Scalable Alignment","created":"2025-07-06","cited_by_count":6,"area":"lr"},{"id":"2602.23802","title":"EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models","created":"2026-02-27","cited_by_count":5,"area":"lr"},{"id":"2511.18242","title":"EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning","created":"2025-11-23","cited_by_count":4,"area":"lr"},{"id":"2509.08105","title":"MERLIN: Multi-Stage Curriculum Alignment for Multilingual Encoder-LLM Integration in Cross-Lingual Reasoning","created":"2025-09-09","cited_by_count":2,"area":"lr"},{"id":"2602.24283","title":"Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation","created":"2026-02-27","cited_by_count":2,"area":"lr"},{"id":"2605.20066","title":"Text-to-SPARQL Generation with Reinforcement Learning: A GRPO-based Approach on DBLP","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2607.03065","title":"Spectral Rewiring for Exploration, Purification, and Model Merging","created":"2026-07-03","cited_by_count":1,"area":"lr"},{"id":"2508.10123","title":"Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts","created":"2025-08-13","cited_by_count":0,"area":"lr"},{"id":"2512.23073","title":"Rethinking Fine-Tuning: Unlocking Hidden Capabilities in Vision-Language Models","created":"2025-12-28","cited_by_count":0,"area":"lr"},{"id":"2602.19169","title":"Virtual Parameter Sharpening: Dynamic Low-Rank Perturbations for Inference-Time Reasoning Enhancement","created":"2025-12-02","cited_by_count":0,"area":"lr"},{"id":"2606.19944","title":"Timage: A Generative Text-in-Image Paradigm for Fine-Tuning Vision-Language Models","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"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":"2609.23205","title":"Euston: Training Away Mathematical Sycophancy Without Losing the Mathematics","created":"2026-09-19","cited_by_count":0,"area":"lr"},{"id":"2610.16489","title":"Growing and Transferring Pathways for LLM Reinforcement Learning","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}