Image de couverture de livre

GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Minghan, Bai, Ye, Vu, Thuy-Trang, Shareghi, Ehsan, Haffari, Gholamreza
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Towards Inference-time Scaling for Continuous Space Reasoning
par: Wang, Minghan, et autres
Publié: (2025)

Discrete Minds in a Continuous World: Do Language Models Know Time Passes?
par: Wang, Minghan, et autres
Publié: (2025)

SpeechDialogueFactory: Generating High-Quality Speech Dialogue Data to Accelerate Your Speech-LLM Development
par: Wang, Minghan, et autres
Publié: (2025)

Exploring the Potential of Multimodal LLM with Knowledge-Intensive Multimodal ASR
par: Wang, Minghan, et autres
Publié: (2024)

Conversational SimulMT: Efficient Simultaneous Translation with Large Language Models
par: Wang, Minghan, et autres
Publié: (2024)

Beyond Imitation: Recovering Dense Rewards from Demonstrations
par: Li, Jiangnan, et autres
Publié: (2025)

Active Continual Learning: On Balancing Knowledge Retention and Learnability
par: Vu, Thuy-Trang, et autres
Publié: (2023)

Simultaneous Machine Translation with Large Language Models
par: Wang, Minghan, et autres
Publié: (2023)

Continual Learning for Large Language Models: A Survey
par: Wu, Tongtong, et autres
Publié: (2024)

MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning
par: Bai, Ye, et autres
Publié: (2025)

SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking
par: Liu, Junnan, et autres
Publié: (2025)

AIPO: Learning to Reason from Active Interaction
par: Liu, Junnan, et autres
Publié: (2026)

The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph
par: Wu, Minghao, et autres
Publié: (2024)

Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models
par: Wu, Minghao, et autres
Publié: (2024)

Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models
par: Yang, Hao, et autres
Publié: (2024)

Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs
par: Nguyen, Minh-Vuong, et autres
Publié: (2024)

Resurfacing Paralinguistic Awareness in Large Audio Language Models
par: Yang, Hao, et autres
Publié: (2026)

Inference-Time Rethinking with Latent Thought Vectors for Math Reasoning
par: Kong, Deqian, et autres
Publié: (2026)

Towards Probing Speech-Specific Risks in Large Multimodal Models: A Taxonomy, Benchmark, and Insights
par: Yang, Hao, et autres
Publié: (2024)

Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models
par: Yang, Hao, et autres
Publié: (2024)

Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models
par: Yang, Hao, et autres
Publié: (2025)

One STEP at a time: Language Agents are Stepwise Planners
par: Nguyen, Minh, et autres
Publié: (2024)

Adapting Large Language Models for Document-Level Machine Translation
par: Wu, Minghao, et autres
Publié: (2024)

Latent Thought Models with Variational Bayes Inference-Time Computation
par: Kong, Deqian, et autres
Publié: (2025)

Extending LLMs to New Languages: A Case Study of Llama and Persian Adaptation
par: Sani, Samin Mahdizadeh, et autres
Publié: (2024)

IRIS: An Iterative and Integrated Framework for Verifiable Causal Discovery in the Absence of Tabular Data
par: Feng, Tao, et autres
Publié: (2025)

IntroLM: Introspective Language Models via Prefilling-Time Self-Evaluation
par: Kasnavieh, Hossein Hosseini, et autres
Publié: (2026)

CONGRAD:Conflicting Gradient Filtering for Multilingual Preference Alignment
par: Li, Jiangnan, et autres
Publié: (2025)

SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models
par: Li, Zhuang, et autres
Publié: (2024)

TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law
par: Hui, Zheng, et autres
Publié: (2025)

Reasoning to Learn from Latent Thoughts
par: Ruan, Yangjun, et autres
Publié: (2025)

Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models
par: Jin, Rihui, et autres
Publié: (2025)

Parallel Test-Time Scaling for Latent Reasoning Models
par: You, Runyang, et autres
Publié: (2025)

Logical Reasoning with Outcome Reward Models for Test-Time Scaling
par: Thatikonda, Ramya Keerthy, et autres
Publié: (2025)

Reasoning with Latent Thoughts: On the Power of Looped Transformers
par: Saunshi, Nikunj, et autres
Publié: (2025)

Proverbs Run in Pairs: Evaluating Proverb Translation Capability of Large Language Model
par: Wang, Minghan, et autres
Publié: (2025)

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
par: Geiping, Jonas, et autres
Publié: (2025)

Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute
par: Liu, Sheng, et autres
Publié: (2025)

MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
par: Liu, Akide, et autres
Publié: (2024)

ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates
par: Yang, Ling, et autres
Publié: (2025)