Image de couverture de livre

SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ho, Sy-Tuyen, Liu, Minghui, Nghiem, Huy, Huang, Furong
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SoundnessBench: A Soundness Benchmark for Neural Network Verifiers
par: Zhou, Xingjian, et autres
Publié: (2024)

Agentic Critical Training
par: Liu, Weize, et autres
Publié: (2026)

Imitate the Good and Avoid the Bad: An Incremental Approach to Safe Reinforcement Learning
par: Hoang, Huy, et autres
Publié: (2023)

MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?
par: Chen, Zhaorun, et autres
Publié: (2024)

VeriGate: Verifier-Gated Step-Level Supervision for GRPO
par: Agrawal, Aakriti, et autres
Publié: (2026)

Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights
par: Ho, Sy-Tuyen, et autres
Publié: (2025)

Model Inversion Robustness: Can Transfer Learning Help?
par: Ho, Sy-Tuyen, et autres
Publié: (2024)

Do Vision-Language Models Leak What They Learn? Adaptive Token-Weighted Model Inversion Attacks
par: Nguyen, Ngoc-Bao, et autres
Publié: (2025)

AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators
par: Mazumder, Aritra, et autres
Publié: (2026)

Hypernetwork-Driven Low-Rank Adaptation Across Attention Heads
par: Diep, Nghiem T., et autres
Publié: (2025)

Revisiting Model Inversion Evaluation: From Misleading Standards to Reliable Privacy Assessment
par: Ho, Sy-Tuyen, et autres
Publié: (2025)

Good Allocations from Bad Estimates
par: Casacuberta, Sílvia, et autres
Publié: (2026)

SmartBench: Is Your LLM Truly a Good Chinese Smartphone Assistant?
par: Lu, Xudong, et autres
Publié: (2025)

Bias in the Tails: How Name-conditioned Evaluative Framing in Resume Summaries Destabilizes LLM-based Hiring
par: Nghiem, Huy, et autres
Publié: (2026)

Vertical Federated Learning in Practice: The Good, the Bad, and the Ugly
par: Wu, Zhaomin, et autres
Publié: (2025)

Agent Performing Autonomous Stock Trading under Good and Bad Situations
par: Luo, Yunfei, et autres
Publié: (2023)

Sequence-Aware Inline Measurement Attribution for Good-Bad Wafer Diagnosis
par: Miyaguchi, Kohei, et autres
Publié: (2025)

When Bad Data Leads to Good Models
par: Li, Kenneth, et autres
Publié: (2025)

Know Your Scientist: KYC as Biosecurity Infrastructure
par: Feldman, Jonathan, et autres
Publié: (2026)

Do Two AI Scientists Agree?
par: Fu, Xinghong, et autres
Publié: (2025)

DoRAN: Stabilizing Weight-Decomposed Low-Rank Adaptation via Noise Injection and Auxiliary Networks
par: Diep, Nghiem T., et autres
Publié: (2025)

Beware! The AI Act Can Also Apply to Your AI Research Practices
par: Wernick, Alina, et autres
Publié: (2025)

Are Synthetic Time-series Data Really not as Good as Real Data?
par: Fu, Fanzhe, et autres
Publié: (2024)

Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
par: Tang, Kaihua, et autres
Publié: (2020)

The Good, The Bad, and The Hybrid: A Reward Structure Showdown in Reasoning Models Training
par: Sahoo, Subramanyam
Publié: (2025)

Idea2Plan: Exploring AI-Powered Research Planning
par: Huang, Jin, et autres
Publié: (2025)

Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
par: Zhang, Qingru, et autres
Publié: (2023)

FADE: Why Bad Descriptions Happen to Good Features
par: Puri, Bruno, et autres
Publié: (2025)

The Good, the Bad, and the Ugly: The Role of AI Quality Disclosure in Lie Detection
par: Bhattacharya, Haimanti, et autres
Publié: (2024)

Ambient Diffusion Omni: Training Good Models with Bad Data
par: Daras, Giannis, et autres
Publié: (2025)

Can AI Scientist Agents Learn from Lab-in-the-Loop Feedback? Evidence from Iterative Perturbation Discovery
par: Wainrib, Gilles, et autres
Publié: (2026)

Conformalized Exceptional Model Mining: Telling Where Your Model Performs (Not) Well
par: Du, Xin, et autres
Publié: (2025)

Bad Values but Good Behavior: Learning Highly Misspecified Bandits and MDPs
par: Banerjee, Debangshu, et autres
Publié: (2023)

Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?
par: Bengio, Yoshua, et autres
Publié: (2025)

The AI Data Scientist
par: Akimov, Farkhad, et autres
Publié: (2025)

On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation
par: Diep, Nghiem T., et autres
Publié: (2025)

Towards a Medical AI Scientist
par: Wu, Hongtao, et autres
Publié: (2026)

When Good Equations Get Bad Scores: Improving Symbolic Regression Through Better Parameter Optimization
par: Wang, Boxiao, et autres
Publié: (2026)

GUIDE: Towards Scalable Advising for Research Ideas
par: Liu, Yaowenqi, et autres
Publié: (2025)

Good Actions Succeed, Bad Actions Generalize: A Case Study on Why RL Generalizes Better
par: Song, Meng
Publié: (2025)