Copertina

Evaluating Parameter Efficient Methods for RLVR

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yin, Qingyu, Wu, Yulun, Shen, Zhennan, Li, Sunbowen, Wang, Zhilin, Li, Yanshu, Leong, Chak Tou, Kang, Jiale, Gu, Jinjin
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning
di: Yin, Qingyu, et al.
Pubblicazione: (2024)

STeCa: Step-level Trajectory Calibration for LLM Agent Learning
di: Wang, Hanlin, et al.
Pubblicazione: (2025)

Merlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting
di: Xia, Heming, et al.
Pubblicazione: (2025)

SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution
di: Wang, Hanlin, et al.
Pubblicazione: (2025)

Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models
di: Wang, Jian, et al.
Pubblicazione: (2025)

Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering
di: Leong, Chak Tou, et al.
Pubblicazione: (2026)

Data-Efficient RLVR via Off-Policy Influence Guidance
di: Zhu, Erle, et al.
Pubblicazione: (2025)

Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region
di: Leong, Chak Tou, et al.
Pubblicazione: (2025)

Improving Sampling Efficiency in RLVR through Adaptive Rollout and Response Reuse
di: Zhang, Yuheng, et al.
Pubblicazione: (2025)

Probing the Difficulty Perception Mechanism of Large Language Models
di: Lee, Sunbowen, et al.
Pubblicazione: (2025)

Protein as a Second Language for LLMs
di: Chen, Xinhui, et al.
Pubblicazione: (2025)

QET: Enhancing Quantized LLM Parameters and KV cache Compression through Element Substitution and Residual Clustering
di: Wang, Yanshu, et al.
Pubblicazione: (2024)

When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification
di: Zhao, Jiale, et al.
Pubblicazione: (2026)

Self-Distilled RLVR
di: Yang, Chenxu, et al.
Pubblicazione: (2026)

JudgeRLVR: Judge First, Generate Second for Efficient Reasoning
di: Duo, Jiangshan, et al.
Pubblicazione: (2026)

Induction Head Toxicity Mechanistically Explains Repetition Curse in Large Language Models
di: Wang, Shuxun, et al.
Pubblicazione: (2025)

Not only where, But when: Temporal Scheduling for RLVR
di: Zhang, Jinghao, et al.
Pubblicazione: (2026)

RLVR-World: Training World Models with Reinforcement Learning
di: Wu, Jialong, et al.
Pubblicazione: (2025)

RLVR Training of LLMs Does Not Improve Thinking Ability for General QA: Evaluation Method and a Simple Solution
di: Li, Kaiyuan, et al.
Pubblicazione: (2026)

When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR
di: Miao, Yuchun, et al.
Pubblicazione: (2026)

Counterfactual experience augmented off-policy reinforcement learning
di: Lee, Sunbowen, et al.
Pubblicazione: (2025)

WIMLE: Uncertainty-Aware World Models with IMLE for Sample-Efficient Continuous Control
di: Aghabozorgi, Mehran, et al.
Pubblicazione: (2026)

ELAS: Efficient Pre-Training of Low-Rank Large Language Models via 2:4 Activation Sparsity
di: Li, Jiaxi, et al.
Pubblicazione: (2026)

Efficiently Aligning Draft Models via Parameter- and Data-Efficient Adaptation
di: Lin, Luxi, et al.
Pubblicazione: (2026)

IRDS: Interpretable RLVR Data Selection via Verifier-Coupled Sparse Autoencoder Coverage
di: Li, Yuhan, et al.
Pubblicazione: (2026)

Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
di: Yin, Qingyu, et al.
Pubblicazione: (2025)

Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning
di: Wu, Junkang, et al.
Pubblicazione: (2025)

ParamReL: Learning Parameter Space Representation via Progressively Encoding Bayesian Flow Networks
di: Wu, Zhangkai, et al.
Pubblicazione: (2024)

Asymmetric Advantage Modulation Calibrates Entropy Dynamics in RLVR
di: Gu, Hengrui, et al.
Pubblicazione: (2026)

Beyond Variance: Prompt-Efficient RLVR via Rare-Event Amplification and Bidirectional Pairing
di: Pang, Yujuan, et al.
Pubblicazione: (2026)

Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
di: Chen, Peter, et al.
Pubblicazione: (2025)

Efficient RLVR Training via Weighted Mutual Information Data Selection
di: Zhou, Xinyu, et al.
Pubblicazione: (2026)

Symbolic Representation for Any-to-Any Generative Tasks
di: Chen, Jiaqi, et al.
Pubblicazione: (2025)

Athena: Efficient Block-Wise Post-Training Quantization for Large Language Models Using Second-Order Matrix Derivative Information
di: Wang, Yanshu, et al.
Pubblicazione: (2024)

On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
di: Huang, Kexin, et al.
Pubblicazione: (2026)

PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective
di: Huang, Yangyi, et al.
Pubblicazione: (2026)

Where to Spend Rollouts: Hit-Utility Optimal Rollout Allocation for Group-Based RLVR
di: Wang, Tao, et al.
Pubblicazione: (2026)

SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs
di: Lee, Chanuk, et al.
Pubblicazione: (2026)

Linear Dynamics in the RLVR Training of Large Language Models
di: Wang, Tianle, et al.
Pubblicazione: (2026)

Uniform-Correct Policy Optimization: Breaking RLVR's Indifference to Diversity
di: Lochab, Anamika, et al.
Pubblicazione: (2026)