{"total":28,"rows":[{"id":"2502.11740","title":"Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent","created":"2025-02-17","cited_by_count":13,"area":"lr"},{"id":"2503.04872","title":"TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation","created":"2025-03-06","cited_by_count":12,"area":"lr"},{"id":"2602.12566","title":"To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2504.10766","title":"How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients","created":"2025-04-14","cited_by_count":8,"area":"lr"},{"id":"2602.21189","title":"Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training","created":"2026-02-24","cited_by_count":8,"area":"lr"},{"id":"2601.07389","title":"On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training","created":"2026-01-12","cited_by_count":6,"area":"lr"},{"id":"2603.04772","title":"TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings","created":"2026-03-05","cited_by_count":6,"area":"lr"},{"id":"2206.03715","title":"Modularized Transfer Learning with Multiple Knowledge Graphs for Zero-shot Commonsense Reasoning","created":"2022-06-08","cited_by_count":5,"area":"lr"},{"id":"2510.21978","title":"Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models","created":"2025-10-24","cited_by_count":5,"area":"lr"},{"id":"2510.07169","title":"More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning","created":"2025-10-08","cited_by_count":4,"area":"lr"},{"id":"2602.06453","title":"On the Plasticity and Stability for Post-Training Large Language Models","created":"2026-02-06","cited_by_count":4,"area":"lr"},{"id":"2602.06359","title":"Training Data Selection with Gradient Orthogonality for Efficient Domain Adaptation","created":"2026-02-06","cited_by_count":3,"area":"lr"},{"id":"2604.27201","title":"Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation","created":"2026-04-29","cited_by_count":3,"area":"lr"},{"id":"2605.14448","title":"Think When Needed: Adaptive Reasoning-Driven Multimodal Embeddings with a Dual-LoRA Architecture","created":"2026-05-14","cited_by_count":3,"area":"lr"},{"id":"2606.02398","title":"A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL","created":"2026-06-01","cited_by_count":3,"area":"lr"},{"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":"2603.20899","title":"Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach","created":"2026-03-21","cited_by_count":2,"area":"lr"},{"id":"2604.19234","title":"Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation","created":"2026-04-21","cited_by_count":2,"area":"lr"},{"id":"2605.25443","title":"Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning Models","created":"2026-05-25","cited_by_count":2,"area":"lr"},{"id":"2605.04330","title":"The Scaling Properties of Implicit Deductive Reasoning in Transformers","created":"2026-05-05","cited_by_count":1,"area":"lr"},{"id":"2606.05025","title":"Invariant Gradient Alignment for Robust Reasoning Distillation","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2607.19341","title":"ExpertVerse: A General-Purpose Benchmark for Expert-Level Reasoning in Knowledge-Intensive Visual Synthesis","created":"2026-07-21","cited_by_count":1,"area":"lr"},{"id":"2609.06469","title":"One Step, One Lead: Mitigating Higher-Order Interference in Multi-Domain Reinforcement Learning via Cross-Step Control","created":"2026-09-06","cited_by_count":1,"area":"lr"},{"id":"2602.08868","title":"AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2603.20020","title":"Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR","created":"2026-03-20","cited_by_count":0,"area":"lr"},{"id":"2606.05800","title":"SALT: When More Rollouts Don't Help in Group-Based Policy Optimization and How to Make Them Matter","created":"2026-06-04","cited_by_count":0,"area":"lr"},{"id":"2608.26587","title":"Surgical Alignment in Knowledge Graph Training for Clinical Diagnosis with Large Language Models","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2609.37203","title":"Learning to Prove, Not Just to Answer: Reinforcement Learning from Formal Verification for Natural-Language Logical Reasoning","created":"2026-09-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}