:: Library Catalog

Image de couverture de livre

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Changming, Banerjee, Debangshu, Vasisht, Deepak, Singh, Gagandeep
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	https://arxiv.org/abs/2504.11831
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Compression Aware Certified Training
par: Xu, Changming, et autres
Publié: (2025)

Cross-Input Certified Training for Universal Perturbations
par: Xu, Changming, et autres
Publié: (2024)

Relational DNN Verification With Cross Executional Bound Refinement
par: Banerjee, Debangshu, et autres
Publié: (2024)

Data Shifts Hurt CoT: A Theoretical Study
par: Yin, Lang, et autres
Publié: (2025)

SEVerA: Verified Synthesis of Self-Evolving Agents
par: Banerjee, Debangshu, et autres
Publié: (2026)

CRANE: Reasoning with constrained LLM generation
par: Banerjee, Debangshu, et autres
Publié: (2025)

DINGO: Constrained Inference for Diffusion LLMs
par: Suresh, Tarun, et autres
Publié: (2025)

Incremental Randomized Smoothing Certification
par: Ugare, Shubham, et autres
Publié: (2023)

Bypassing the Safety Training of Open-Source LLMs with Priming Attacks
par: Vega, Jason, et autres
Publié: (2023)

Towards Generalized Certified Robustness with Multi-Norm Training
par: Jiang, Enyi, et autres
Publié: (2024)

Certifying Knowledge Comprehension in LLMs
par: Chaudhary, Isha, et autres
Publié: (2024)

Towards Reliable Alignment: Uncertainty-aware RLHF
par: Banerjee, Debangshu, et autres
Publié: (2024)

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

Formal Synthesis of Certifiably Robust Neural Lyapunov-Barrier Certificates
par: Wang, Chengxiao, et autres
Publié: (2026)

Probabilistic Trust Intervals for Out of Distribution Detection
par: Singh, Gagandeep, et autres
Publié: (2021)

Evolving Abstract Transformers for Gradient-Guided, Adaptable Abstract Interpretation
par: Gomber, Shaurya, et autres
Publié: (2025)

Certifying Counterfactual Bias in LLMs
par: Chaudhary, Isha, et autres
Publié: (2024)

Towards Reliable, Uncertainty-Aware Alignment
par: Banerjee, Debangshu, et autres
Publié: (2025)

Top-$nσ$: Not All Logits Are You Need
par: Tang, Chenxia, et autres
Publié: (2024)

Accuracy is Not All You Need
par: Dutta, Abhinav, et autres
Publié: (2024)

Why DPO is a Misspecified Estimator and How to Fix It
par: Gopalan, Aditya, et autres
Publié: (2025)

Attention is All You Need Until You Need Retention
par: Yaslioglu, M. Murat
Publié: (2025)

Context is All You Need
par: Delanois, Jean Erik, et autres
Publié: (2026)

Attention Is All You Need But You Don't Need All Of It For Inference of Large Language Models
par: Tyukin, Georgy, et autres
Publié: (2024)

Efficient Deep Learning Board: Training Feedback Is Not All You Need
par: Gong, Lina, et autres
Publié: (2024)

How Catastrophic is Your LLM? Certifying Risk in Conversation
par: Wang, Chengxiao, et autres
Publié: (2025)

Some Attention is All You Need for Retrieval
par: Michalak, Felix, et autres
Publié: (2025)

Half Search Space is All You Need
par: Rumiantsev, Pavel, et autres
Publié: (2025)

Exploitation Is All You Need... for Exploration
par: Rentschler, Micah, et autres
Publié: (2025)

Multistep Inverse Is Not All You Need
par: Levine, Alexander, et autres
Publié: (2024)

Cooperation Is All You Need
par: Adeel, Ahsan, et autres
Publié: (2023)

ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs
par: Yang, Yuchen, et autres
Publié: (2024)

Realizable Learning is All You Need
par: Hopkins, Max, et autres
Publié: (2021)

No More Adam: Learning Rate Scaling at Initialization is All You Need
par: Xu, Minghao, et autres
Publié: (2024)

Revisiting End-To-End Sparse Autoencoder Training: A Short Finetune Is All You Need
par: Karvonen, Adam
Publié: (2025)

BEAVER: An Efficient Deterministic LLM Verifier
par: Suresh, Tarun, et autres
Publié: (2025)

Fusion or Confusion? Multimodal Complexity Is Not All You Need
par: Rheude, Tillmann, et autres
Publié: (2025)

Robust Thompson Sampling Algorithms Against Reward Poisoning Attacks
par: Xu, Yinglun, et autres
Publié: (2024)

MoE Lens -- An Expert Is All You Need
par: Chaudhari, Marmik, et autres
Publié: (2026)

More Agents Is All You Need
par: Li, Junyou, et autres
Publié: (2024)