No article text was recorded for this version.
supervised fine-tuning and reinforcement learning
Version 1 of 1339 papers371 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning
- Blog: Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
- Blog: Mat-Pref: Verifiable-Reward Training Improves Compositional Reasoning in Inorganic Materials
- Blog: BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning
- Blog: Unlocking Zero-Shot Geospatial Reasoning via Indirect Rewards
- Blog: VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics Expressions
- Blog: Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning
- Blog: Flexible Thinking for Multimodal Emotional Support Conversation via Reinforcement Learning
- Blog: CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling
- Blog: DeepRec: Towards a Deep Dive Into the Item Space with Large Language Model Based Recommendation
- Blog: Reasoning Language Models: A Blueprint
- Blog: Graph-R1: Unleashing LLM Reasoning with NP-Hard Graph Problems
- Blog: Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
- Blog: DeepTrans: Deep Reasoning Translation via Reinforcement Learning
- Blog: Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model Learning
- Blog: RecThinker: An Agentic Framework for Tool-Augmented Reasoning in Recommendation
- Blog: UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction-as-Reasoning
- Blog: Towards Next-Generation Recommender Systems: A Benchmark for Personalized Recommendation Assistant with LLMs
- Blog: VisuRiddles: Fine-grained Perception is a Primary Bottleneck for Multimodal Large Language Models in Abstract Visual Reasoning
- Blog: Proofread: Fixes All Errors with One Tap
- Blog: GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagery
- Blog: REAR: Reinforced Reasoning Optimization for Event Argument Extraction with Relation-Aware Support
- Blog: ComfyUI-R1: Exploring Reasoning Models for Workflow Generation
- Blog: Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models
- Blog: AutoDrive-R2: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving.
- Blog: INFMEM: Learning System-2 Memory Control for Long-Context Agent
- Blog: Multimodal Mathematical Reasoning with Diverse Solving Perspective
- Blog: MEDFACT-R1: TOWARDS FACTUAL MEDICAL REASONING VIA PSEUDO-LABEL AUGMENTATION
- Blog: SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning
- Blog: Generate, Not Recommend: Personalized Multimodal Content Generation
- Blog: Improve LLM-as-a-Judge Ability as a General Ability
- Blog: Towards Adaptive Mechanism Activation in Language Agent
- Blog: Thinking in 360°: Humanoid Visual Search in the Wild
- Blog: GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learning
- Blog: Metaphor-based Jailbreaking Attacks on Text-to-Image Models
- Blog: Personalized Exposure Control Using Adaptive Metering and Reinforcement Learning
- Blog: Generating Persona-Consistent Dialogue Responses Using Deep Reinforcement Learning
- Blog: Kardia-R1: Unleashing LLMs to Reason toward Understanding and Empathy for Emotional Support via Rubric-as-Judge Reinforcement Learning
- Blog: BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation
- Blog: PrefGen: A Preference-Driven Methodology for Secure Yet Gas-Efficient Smart Contract Generation
- Blog: ThinkFake: Reasoning in Multimodal Large Language Models for AI-Generated Image Detection
- Blog: Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigm
- Blog: Zooming into Comics: Region-Aware RL Improves Fine-Grained Comic Understanding in Vision-Language Models
- Blog: Kwai Keye-VL Technical Report
- Blog: Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learning
- Blog: SR: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning
- Blog: Can Open Large Language Models Catch Vulnerabilities?
- Blog: SynthRL: Cross-domain Synthesizer Sound Matching via Reinforcement Learning
- Blog: Omni-CLST: Error-aware Curriculum Learning with guided Selective chain-of-Thought for audio question answering
- Blog: Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning
- Blog: Value Alignment from Unstructured Text
- Blog: Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing
- Blog: Autonomous Driving System based on Dual Process Theory and Deliberate Practice Theory
- Blog: Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models
- Blog: Unleashing Scientific Reasoning for Bio-experimental Protocol Generation via Structured Component-based Reward Mechanism
- Blog: RULE: Reinforcement UnLEarning Achieves Forget-Retain Pareto Optimality
- Blog: ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking
- Blog: AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play
- Blog: What is the Visual Cognition Gap between Humans and Multimodal LLMs?
- Blog: R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization
Showing 60 of 339 papers.
History & citation
Current · Permanent link
- Post-Training Recipes for Large Reasoning Models merged into this direction (56% overlap)
- Staged Policy Refinement for Agentic Reasoning and Tool Use merged into this direction (52% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_supervised_fine_tuning_and_reinforcement_40f26a8b,
title = {supervised fine-tuning and reinforcement learning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/supervised-fine-tuning-and-reinforcement-learning/rdr_40f26a8b0db64423aba522f24c4e5419},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_supervised_fine_tuning_and_reinforcement_40f26a8b_v1,
title = {supervised fine-tuning and reinforcement learning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/supervised-fine-tuning-and-reinforcement-learning/rdr_40f26a8b0db64423aba522f24c4e5419/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}