PAC-CF introduces a method called Probably Approximately Correct Conformal Filtering to calibrate irreversible frontier pruning in large language model (LLM)-guided search. The approach treats tree pruning as a PAC‑guaranteed decision problem, deriving a conformal margin from score deficits on held‑out Native traces and applying a direct score‑gap filtering rule during deployment. Experiments across multiple domains and controllers show that PAC‑CF improves utility at various budgets and reduces workload metrics, notably boosting equal‑domain utility by 4.38 points and cutting physical requests by 18.95% with a 23.76% token reduction on a pruning‑aware ToolTree under a 100‑request budget.
By Tianhao Qian, Jiayu Chen, Lixu Wang
arXiv:2512.03491v3 Announce Type: replace
Abstract: Neural Networks are indispensable to natural sciences and society. Their impact extends from applications in public health to workforce productivit...
By Antonin Sulc, Noor Naddour
The paper demonstrates that image knowledge distillation can be backdoored even when the teacher model is clean, by poisoning the distillation dataset with triggered and manipulated images that the teacher already classifies as a target label. The attack, effective at poisoning rates as low as 10%, uses targeted adversarial perturbations and GAN-based class transitions to embed a backdoor into the student model while preserving its performance on clean data. The study highlights that the security of knowledge distillation depends not only on the teacher but also on the integrity of the distillation data.
By Qian Ma, Chen Wu, Prasenjit Mitra, Sencun Zhu
arXiv:2507.19364v3 Announce Type: replace
Abstract: The integration of Large Language Models (LLMs) into social simulation has generated considerable enthusiasm, but also raises substantial methodolo...
By Patrick Taillandier, Jean Daniel Zucker, Arnaud Grignard, Benoit Gaudou, Nghi Quang Huynh, Haojia Kong, Alexis Drogoul
arXiv:2609.10296v1 Announce Type: new
Abstract: Non-invasive speech decoding remains constrained by the low signal-to-noise ratio of neural recordings, which makes fine-grained reconstruction of phon...
By Gilad D. Landau, Dulhan Jayalath, Oiwi Parker Jones
arXiv:2609.07937v1 Announce Type: cross
Abstract: Structured visual reasoning, such as image puzzles, demands fine-grained visual perception, an ability current Vision Language Models (VLMs) lack. VL...
By Harsha Patnala, Debopriyo Banerjee, Ayush Sunil Munot, Somak Aditya
arXiv:2609.10002v1 Announce Type: new
Abstract: Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and t...
By Rafael M. Mamede, Pedro C. Neto, Ana F. Sequeira
The paper introduces Suan, a new preference optimization algorithm designed to improve safety alignment in large language models. Suan operates directly at the gradient level, avoiding traditional variational derivations, which yields more interpretable and robust training dynamics. Experiments show that Suan outperforms existing methods, achieving superior safety alignment while maintaining response utility.
By Oleksandr Cherednichenko, Roman Klypa
arXiv:2609.08333v1 Announce Type: cross
Abstract: In molecular discovery, molecule size is coupled to composition, structure, and other target properties. Yet most 3D generators require molecule size...
By Weichi Yao, Cameron Gruich, Bryan R. Goldsmith, Yixin Wang
The fusion of hyperspectral (HS) and Light Detection and Ranging (LiDAR) data plays a crucial role in enhancing land-cover classification by jointly exploiting spectral, spatial, and structural cues....
AI agents increasingly act through tools and delegated authority, but general incident repositories rarely capture the mechanisms needed to compare public failures with agent-security evaluations. We...
Studies of the Model Context Protocol (MCP) server ecosystem draw their samples in ways that quietly select for servers that work: reference sets, popularity lists, hand-curated frames, or pipelines t...
P300 brain-computer interface (BCI) spellers can provide hands-free communication for people with severe motor impairments. Modern pipelines combine multiple individually promising components, often a...
Paul Christiano has joined the OpenAI Foundation Board and its Safety and Security Committee. His appointment brings experience in AI alignment, safety, and standards to the organization.
Large Language Models (LLMs) can memorize and reproduce sensitive, copyrighted, or otherwise undesirable training content, creating privacy, safety, and regulatory concerns. Machine unlearning offers...
Algorithmic stability refers to the property of an algorithm being insensitive to perturbations of the input data, where the type of perturbation may vary depending on the setting. In this work, we de...
Uncertainty estimation for medical vision--language models (VLMs) using conformal prediction has gained increasing attention due to its distribution-free coverage guarantees. However, standard conform...
Data augmentation is fundamental to training modern deep vision and multimodal models. While individual methods, such as RandAug, CutMix, Mixup, RandErase, and DropPath, offer strong regularization ef...
Open-source large language models (LLMs) are increasingly competitive with closed-source models while offering transparency and the ability to run inference without exposing user inputs to a service p...
Large language models remain fragile against malicious fine-tuning, motivating training-time defenses against harmful persona drift. Preventative Steering injects undesirable-trait persona vectors dur...