Key Highlights: Europe is one of the markets across the globe where tech giants find themselves under heavy scrutiny from the European Commission. Meta, this time, has found itself in a spot of bother after introducing a WhatsApp policy that blocks third-party AI providers.  Italy’s antitrust regulator asks Meta to suspend its WhatsApp policy that blocks third-party AI providers Earlier this month, the European Commission launched a separate investigation into this matter. At the time, the regulator announced […]

Ver mais

arXiv:2601.19944v1 Announce Type: cross Abstract: We study model-agnostic post-hoc calibration methods intended to improve probabilistic predictions in supervised binary classification on real i.i.d. tabular data, with particular emphasis on conformal and Venn-based approaches that provide distribution-free validity guarantees under exchangeability. We benchmark 21 widely used classifiers, including linear models, SVMs, tree ensembles (CatBoost, XGBoost, LightGBM), and modern tabular neural and foundation models, on binary tasks from the TabArena-v0.1 suite using randomized, stratified five-fold cross-validation with a held-out test […]

Ver mais

arXiv:2604.15400v1 Announce Type: new Abstract: We present causal evidence that hallucination in autoregressive language models is an early trajectory commitment governed by asymmetric attractor dynamics. Using same-prompt bifurcation, in which we repeatedly sample identical inputs to observe spontaneous divergence, we isolate trajectory dynamics from prompt-level confounds. On Qwen2.5-1.5B across 61 prompts spanning six categories, 27 prompts (44.3%) bifurcate with factual and hallucinated trajectories diverging at the first generated token (KL = 0 at step 0, KL > 1.0 […]

Ver mais

arXiv:2602.15222v1 Announce Type: new Abstract: Reward models are central to large language model (LLM) post-training. However, past work has shown that they can reward spurious or undesirable attributes such as length, format, hallucinations, and sycophancy. In this work, we introduce and study the research problem of automatically finding reward model biases in natural language. We offer a simple approach of using an LLM to iteratively propose and refine candidate biases. Our method can recover known biases and surface […]

Ver mais

Generative AI is extremely appealing for non-technical users, who feel like they’ve gained access to magic powers. But as this story shows, a little knowledge is a dangerous thing. The Magic Genie Once upon a time, there was a Chief Data Officer who believed that the new wave of Generative AI, such as ChatGPT and Gemini, could bridge any technical hurdle. At a local AI meetup, they met a founder with no technical background who had proudly built […]

Ver mais

arXiv:2603.06698v1 Announce Type: new Abstract: Knowledge distillation between asymmetric architectures often induces severe geometric constraints on the learned representation space. In this work, we investigate the Dimensional Collapse phenomenon when distilling a 500M parameter global Vision Transformer (CLIP ViT-B/32) into strictly capacity-constrained, local-receptive-field CNNs (0.5M to 8.0M parameters) on the CIFAR-10 dataset. By employing strictly centered Singular Value Decomposition (SVD) and Variance-based Shannon Entropy Effective Rank, we isolate true structural variance from mean-vector artifacts. Our empirical results demonstrate […]

Ver mais

The life of a prescription at Amazon Pharmacy From pricing estimation and regulatory compliance to inventory management and chatbot assistants, machine learning models help Amazon Pharmacy customers stay healthy and save time and money. Conversational AI Alexandre Alves Anita Vila September 30, 01:32 PM October 02, 11:42 AM Pharmacies play a vital role in ensuring patients health, but the process of dispensing medications is far more complex than it may appear. At Amazon Pharmacy, we are using artificial […]

Ver mais

arXiv:2506.20779v4 Announce Type: replace Abstract: We study the implicit bias of flatness / low (loss) curvature and its effects on generalization in two-layer overparameterized ReLU networks with multivariate inputs — a problem well motivated by the minima stability and edge-of-stability phenomena in gradient-descent training. Existing work either requires interpolation or focuses only on univariate inputs. This paper presents new and somewhat surprising theoretical results for multivariate inputs. On two natural settings (1) generalization gap for flat solutions, and […]

Ver mais

arXiv:2601.05257v1 Announce Type: new Abstract: Sponsored search advertising (SSA) requires advertisers to constantly adjust keyword strategies. While bid adjustment and keyword generation are well-studied, keyword pruning-refining keyword sets to enhance campaign performance-remains under-explored. This paper addresses critical inefficiencies in current practices as evidenced by a dataset containing 0.5 million SSA records from a pharmaceutical advertiser on search engine Meituan, China’s largest delivery platform. We propose KP-Agent, an LLM agentic system with domain tool set and a memory module. […]

Ver mais