Imagen de Portada

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xuan, Richmond Sin Jing, Bhardwaj, Rishabh, Poria, Soujanya
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic
por: Bhardwaj, Rishabh, et al.
Publicado: (2024)

OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!
por: Lei, Jingdi, et al.
Publicado: (2025)

Towards Robust Instruction Tuning on Multimodal Large Language Models
por: Han, Wei, et al.
Publicado: (2024)

The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles
por: Toh, Vernon Y. H., et al.
Publicado: (2025)

Uncovering Cross-Linguistic Disparities in LLMs using Sparse Autoencoders
por: Xuan, Richmond Sin Jing, et al.
Publicado: (2025)

DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
por: Deep, Pala Tej, et al.
Publicado: (2024)

Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming
por: Han, Vernon Toh Yan, et al.
Publicado: (2024)

Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision
por: Pala, Tej Deep, et al.
Publicado: (2025)

Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model
por: Kang, Jaeyong, et al.
Publicado: (2023)

Are Language Models Puzzle Prodigies? Algorithmic Puzzles Unveil Serious Challenges in Multimodal Reasoning
por: Ghosal, Deepanway, et al.
Publicado: (2024)

Stacked from One: Multi-Scale Self-Injection for Context Window Extension
por: Han, Wei, et al.
Publicado: (2026)

Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned
por: Ong, Brandon, et al.
Publicado: (2025)

WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models
por: Gupta, Prannaya, et al.
Publicado: (2024)

Two are better than one: Context window extension with multi-grained self-injection
por: Han, Wei, et al.
Publicado: (2024)

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning
por: Sun, Qi, et al.
Publicado: (2024)

Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths
por: Chia, Yew Ken, et al.
Publicado: (2024)

Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models
por: Han, Wei, et al.
Publicado: (2023)

Can-Do! A Dataset and Neuro-Symbolic Grounded Framework for Embodied Planning with Large Multimodal Models
por: Chia, Yew Ken, et al.
Publicado: (2024)

Large Language Models for Automated Open-domain Scientific Hypotheses Discovery
por: Yang, Zonglin, et al.
Publicado: (2023)

Toward Robust Multimodal Learning using Multimodal Foundational Models
por: Zhao, Xianbing, et al.
Publicado: (2024)

Thinking About Thinking: Evaluating Reasoning in Post-Trained Language Models
por: Singla, Pratham, et al.
Publicado: (2025)

Beyond What to Select: A Plug-and-play Oscillatory Data-Volume Scheduling for Efficient Model Training
por: Yang, Suorong, et al.
Publicado: (2026)

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning
por: Gan, Siyuan, et al.
Publicado: (2026)

Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training
por: Park, Yein, et al.
Publicado: (2025)

NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks
por: Hung, Chia-Yu, et al.
Publicado: (2025)

HyperTTS: Parameter Efficient Adaptation in Text to Speech using Hypernetworks
por: Li, Yingting, et al.
Publicado: (2024)

Computational Irreducibility as the Foundation of Agency: A Formal Model Connecting Undecidability to Autonomous Behavior in Complex Systems
por: Azadi, Poria
Publicado: (2025)

DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priors
por: Rakib, Tazeek Bin Abdur, et al.
Publicado: (2025)

Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents
por: Dong, Yanfei, et al.
Publicado: (2024)

$δ$-mem: Efficient Online Memory for Large Language Models
por: Lei, Jingdi, et al.
Publicado: (2026)

NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards
por: Hung, Chia-Yu, et al.
Publicado: (2025)

Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
por: An, Sohyun, et al.
Publicado: (2025)

Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique
por: Pala, Tej Deep, et al.
Publicado: (2024)

JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment
por: Liu, Renhang, et al.
Publicado: (2025)

10 Open Challenges Steering the Future of Vision-Language-Action Models
por: Poria, Soujanya, et al.
Publicado: (2025)

MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses
por: Yang, Zonglin, et al.
Publicado: (2024)

PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost
por: Yi, Junkeun, et al.
Publicado: (2026)

LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions
por: Song, Maojia, et al.
Publicado: (2025)

Efficient Reasoning with Hidden Thinking
por: Shen, Xuan, et al.
Publicado: (2025)

Think First, Diffuse Fast: Improving Diffusion Language Model Reasoning via Autoregressive Plan Conditioning
por: Sauver, Earl J St
Publicado: (2026)