:: Library Catalog

Copertina

Salvato in:

Dettagli Bibliografici
Autore principale:	Sahoo, Subramanyam
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	https://arxiv.org/abs/2512.13821
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

The Deepfake Detective: Interpreting Neural Forensics Through Sparse Features and Manifolds
di: Sahoo, Subramanyam, et al.
Pubblicazione: (2025)

Calibration Collapse Under Sycophancy Fine-Tuning: How Reward Hacking Breaks Uncertainty Quantification in LLMs
di: Sahoo, Subramanyam
Pubblicazione: (2026)

The Horcrux: Mechanistically Interpretable Task Decomposition for Detecting and Mitigating Reward Hacking in Embodied AI Systems
di: Sahoo, Subramanyam, et al.
Pubblicazione: (2025)

Multi-Agent Systems Execute Arbitrary Malicious Code
di: Triedman, Harold, et al.
Pubblicazione: (2025)

Boardwalk Empire: How Generative AI is Revolutionizing Economic Paradigms
di: Sahoo, Subramanyam, et al.
Pubblicazione: (2024)

Position: The Complexity of Perfect AI Alignment -- Formalizing the RLHF Trilemma
di: Sahoo, Subramanyam, et al.
Pubblicazione: (2025)

I Can't Believe It's Not Robust: Catastrophic Collapse of Safety Classifiers under Embedding Drift
di: Sahoo, Subramanyam, et al.
Pubblicazione: (2026)

When Shallow Wins: Silent Failures and the Depth-Accuracy Paradox in Latent Reasoning
di: Sahoo, Subramanyam, et al.
Pubblicazione: (2026)

SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement
di: Sahoo, Subramanyam, et al.
Pubblicazione: (2026)

The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness
di: Sahoo, Subramanyam, et al.
Pubblicazione: (2026)

Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code
di: Vashishtha, Aniket, et al.
Pubblicazione: (2025)

Towards Effectively Leveraging Execution Traces for Program Repair with Code LLMs
di: Haque, Mirazul, et al.
Pubblicazione: (2025)

GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models
di: Islah, Nizar, et al.
Pubblicazione: (2024)

GasTrace: Detecting Sandwich Attack Malicious Accounts in Ethereum
di: Liu, Zekai, et al.
Pubblicazione: (2024)

VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation
di: Zheng, Yan, et al.
Pubblicazione: (2026)

Scaling Laws Revisited: Modeling the Role of Data Quality in Language Model Pretraining
di: Subramanyam, Anirudh, et al.
Pubblicazione: (2025)

Towards Quantum Machine Learning for Malicious Code Analysis
di: Lopez, Jesus, et al.
Pubblicazione: (2025)

Localizing Malicious Outputs from CodeLLM
di: Borana, Mayukh, et al.
Pubblicazione: (2025)

Keypoint Aware Masked Image Modelling
di: Krishna, Madhava, et al.
Pubblicazione: (2024)

Malicious and Unintentional Disclosure Risks in Large Language Models for Code Generation
di: Rabin, Rafiqul, et al.
Pubblicazione: (2025)

Learning Unmasking Policies for Diffusion Language Models
di: Jazbec, Metod, et al.
Pubblicazione: (2025)

MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?
di: Wahed, Muntasir, et al.
Pubblicazione: (2025)

Self-Execution Simulation Improves Coding Models
di: Maimon, Gallil, et al.
Pubblicazione: (2026)

Detecting Malicious AI Agents Through Simulated Interactions
di: Pi, Yulu, et al.
Pubblicazione: (2025)

Unmasking Trees for Tabular Data
di: McCarter, Calvin
Pubblicazione: (2024)

Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning
di: Li, Yichen, et al.
Pubblicazione: (2024)

Autonomous Vehicle Decision-Making Framework for Considering Malicious Behavior at Unsignalized Intersections
di: Li, Qing, et al.
Pubblicazione: (2024)

FreeMOCA: Memory-Free Continual Learning for Malicious Code Analysis
di: Asadi, Zahra, et al.
Pubblicazione: (2026)

Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates
di: Yue, Kai, et al.
Pubblicazione: (2025)

Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation
di: Yu, Zhuohao, et al.
Pubblicazione: (2024)

Understanding Diffusion Models via Code Execution
di: Yu, Cheng
Pubblicazione: (2025)

Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs
di: Cheng, Ching-An, et al.
Pubblicazione: (2024)

Execution Guided Line-by-Line Code Generation
di: Lavon, Boaz, et al.
Pubblicazione: (2025)

Provably Safe Model Updates
di: Elmecker-Plakolm, Leo, et al.
Pubblicazione: (2025)

Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking
di: Chao, Chen-Hao, et al.
Pubblicazione: (2025)

TaxBreak: Unmasking the Hidden Costs of LLM Inference Through Overhead Decomposition
di: Vellaisamy, Prabhu, et al.
Pubblicazione: (2026)

Execution-Grounded Credit Assignment for GRPO in Code Generation
di: Kumar, Abhijit, et al.
Pubblicazione: (2026)

Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models
di: Lee, Sanghyun, et al.
Pubblicazione: (2025)

Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking
di: Ben-Hamu, Heli, et al.
Pubblicazione: (2025)