Modern AI agents are powerful but often fail to align with the idiosyncratic, evolving preferences of individual users. Prior approaches typically rely on static datasets, either training implicit preference models on interaction history or encoding user profiles in external memory. However, these approaches struggle with new users and with preferences that change over time. We introduce Personalized Agents from Human Feedback (PAHF), a framework for continual personalization in which agents learn online from live interaction using explicit per-user […]

Ver mais

Federated learning (FL) enables collaborative model training without sharing raw data; however, the presence of noisy labels across distributed clients can severely degrade the learning performance. In this paper, we propose FedSIR, a multi-stage framework for robust FL under noisy labels. Different from existing approaches that mainly rely on designing noise-tolerant loss functions or exploiting loss dynamics during training, our method leverages the spectral structure of client feature representations to identify and mitigate label noise. Our framework consists […]

Ver mais

arXiv:2605.28823v1 Announce Type: new Abstract: As the influence of LLMs expands, it is imperative to gain insight into their decisions. One way to do that is to develop probes that detect the presence or absence of a broad set of concepts within the embeddings computed in an LLM – which is what we might say a model is “thinking” about. Such probes should be low-cost and easily applicable to any LLM, so that monitoring for many concepts is […]

Ver mais

arXiv:2602.15871v1 Announce Type: new Abstract: The proliferation of large language models (LLMs) in academic workflows has introduced unprecedented challenges to bibliographic integrity, particularly through reference hallucination — the generation of plausible but non-existent citations. Recent investigations have documented the presence of AI-hallucinated citations even in papers accepted at premier machine learning conferences such as NeurIPS and ICLR, underscoring the urgency of automated verification mechanisms. This paper presents “CheckIfExist”, an open-source web-based tool designed to provide immediate verification of […]

Ver mais

arXiv:2601.16272v1 Announce Type: new Abstract: We present a method for relighting 3D reconstructions of large room-scale environments. Existing solutions for 3D scene relighting often require solving under-determined or ill-conditioned inverse rendering problems, and are as such unable to produce high-quality results on complex real-world scenes. Though recent progress in using generative image and video diffusion models for relighting has been promising, these techniques are either limited to 2D image and video relighting or 3D relighting of individual objects. […]

Ver mais

Kevin Weil’s new role at Stoke Space suggests reusable rockets are the next hot thing in Silicon Valley.

Ver mais

arXiv:2601.12231v1 Announce Type: new Abstract: Insider threat detection is a key challenge in enterprise security, relying on user activity logs that capture rich and complex behavioral patterns. These logs are often multi-channel, non-stationary, and anomalies are rare, making anomaly detection challenging. To address these issues, we propose a novel framework that integrates wavelet-aware modulation, multi-resolution wavelet decomposition, and resolution-adaptive attention for robust anomaly detection. Our approach first applies a deviation-aware modulation scheme to suppress routine behaviors while amplifying […]

Ver mais

Anthropic dropped Claude Opus 4.7. The benchmarks went up. So did everyone’s stress levels after reading the token notes. The internet, as always, found the expensive part first: is Opus 4.7 a genuine breakthrough, or just Opus 4.6 with a tapeworm? source: https://www.instagram.com/chatgptricks?e=76af8cb2-1352-47d9-a03b-9c2eadc90f10&g=5 Anthropic released Claude Opus 4.7 today, April 16, 2026, and at first glance it looks like a straightforward flagship refresh: stronger coding, better long-running task execution, better vision, same headline pricing, and wider availability. Anthropic […]

Ver mais

arXiv:2510.05060v3 Announce Type: replace-cross Abstract: Conformal prediction offers a powerful framework for building distribution-free prediction intervals for exchangeable data. Existing methods that extend conformal prediction to sequential data rely on fitting a relatively complex model to capture temporal dependencies. However, these methods can fail if the sample size is small and often require expensive retraining when the underlying data distribution changes. To overcome these limitations, we propose Reservoir Conformal Prediction (ResCP), a novel training-free conformal prediction method for […]

Ver mais

Recent research shows that Preference Alignment (PA) objectives act as divergence estimators between aligned (chosen) and unaligned (rejected) response distributions. In this work, we extend this divergence-based perspective to general alignment settings, such as reinforcement learning with verifiable rewards (RLVR), where only environmental rewards are available. Within this unified framework, we propose $f$-Group Relative Policy Optimization ($f$-GRPO), a class of on-policy reinforcement learning, and $f$-Hybrid Alignment Loss ($f$-HAL), a hybrid on/off policy objectives, for general LLM alignment based […]

Ver mais