Image de couverture de livre

Does More Inference-Time Compute Really Help Robustness?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wu, Tong, Xiang, Chong, Wang, Jiachen T., Yu, Weichen, Sitawarin, Chawin, Sehwag, Vikash, Mittal, Prateek
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
par: Panda, Ashwinee, et autres
Publié: (2022)

Effectively Controlling Reasoning Models through Thinking Intervention
par: Wu, Tong, et autres
Publié: (2025)

ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search
par: Shen, Zeyu, et autres
Publié: (2025)

PAL: Proxy-Guided Black-Box Attack on Large Language Models
par: Sitawarin, Chawin, et autres
Publié: (2024)

Mark My Words: Analyzing and Evaluating Language Model Watermarks
par: Piet, Julien, et autres
Publié: (2023)

PubDef: Defending Against Transfer Attacks From Public Models
par: Sitawarin, Chawin, et autres
Publié: (2023)

Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice
par: Wang, Jiachen T., et autres
Publié: (2025)

Adapting to Evolving Adversaries with Regularized Continual Robust Training
par: Dai, Sihui, et autres
Publié: (2025)

Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models
par: Ghosal, Soumya Suvra, et autres
Publié: (2025)

Positional Embedding-Aware Activations
par: Shah, Kathan, et autres
Publié: (2023)

PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach
par: Sehwag, Udari Madhushani, et autres
Publié: (2025)

Jatmo: Prompt Injection Defense by Task-Specific Finetuning
par: Piet, Julien, et autres
Publié: (2023)

Finding needles in a haystack: A Black-Box Approach to Invisible Watermark Detection
par: Pan, Minzhou, et autres
Publié: (2024)

Extracting alignment data in open models
par: Barbero, Federico, et autres
Publié: (2025)

Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget
par: Sehwag, Vikash, et autres
Publié: (2024)

Does More Advice Help? The Effects of Second Opinions in AI-Assisted Decision Making
par: Lu, Zhuoran, et autres
Publié: (2024)

Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?
par: Lu, Chengda, et autres
Publié: (2025)

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents?
par: Li, Xinzhe, et autres
Publié: (2026)

Does Homophily Help in Robust Test-time Node Classification?
par: Jiang, Yan, et autres
Publié: (2025)

How to Trace Latent Generative Model Generated Images without Artificial Watermark?
par: Wang, Zhenting, et autres
Publié: (2024)

Safety Alignment Should Be Made More Than Just a Few Tokens Deep
par: Qi, Xiangyu, et autres
Publié: (2024)

OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift
par: Li, Lin, et autres
Publié: (2023)

Does the Question Really Matter? Training-Free Data Selection for Vision-Language SFT
par: Sun, Peng, et autres
Publié: (2026)

Does the Skeleton-Recall Loss Really Work?
par: Arora, Devansh, et autres
Publié: (2025)

Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
par: Wu, Tong, et autres
Publié: (2024)

LLMs Struggle with Abstract Meaning Comprehension More Than Expected
par: Alhazmi, Hamoud, et autres
Publié: (2026)

When More Thinking Hurts: Overthinking in LLM Test-Time Compute Scaling
par: Zhou, Shu, et autres
Publié: (2026)

Context manipulation attacks : Web agents are susceptible to corrupted memory
par: Patlan, Atharv Singh, et autres
Publié: (2025)

XGBoost Learning of Dynamic Wager Placement for In-Play Betting on an Agent-Based Model of a Sports Betting Exchange
par: Terawong, Chawin, et autres
Publié: (2024)

PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses
par: Xiang, Chong, et autres
Publié: (2023)

Beyond Images: Adaptive Fusion of Visual and Textual Data for Food Classification
par: Mittal, Prateek, et autres
Publié: (2023)

With Greater Text Comes Greater Necessity: Inference-Time Training Helps Long Text Generation
par: Wang, Y., et autres
Publié: (2024)

Inference-Time Scaling for Generalist Reward Modeling
par: Liu, Zijun, et autres
Publié: (2025)

Plan-and-Write: Structure-Guided Length Control for LLMs without Model Retraining
par: Akinfaderin, Adewale, et autres
Publié: (2025)

Does Few-Shot Learning Help LLM Performance in Code Synthesis?
par: Xu, Derek, et autres
Publié: (2024)

Does Using Counterfactual Help LLMs Explain Textual Importance in Classification?
par: Tan, Nelvin, et autres
Publié: (2025)

Do Efficient Transformers Really Save Computation?
par: Yang, Kai, et autres
Publié: (2024)

Learnable Chernoff Baselines for Inference-Time Alignment
par: Madhow, Sunil, et autres
Publié: (2026)

Does Synthetic Data Help? Empirical Evidence from Deep Learning Time Series Forecasters
par: Cazaux, Hugo, et autres
Publié: (2026)

One Size Does Not Fit All: A Distribution-Aware Sparsification for More Precise Model Merging
par: Luo, Yingfeng, et autres
Publié: (2025)