Dados & Embeddings — Radar de IA

Position: Evaluation Scores Are Perishable Knowledge Claims

arXiv:2607.26191v1 Announce Type: new Abstract: Evaluation methodologies for language models increasingly combine multiple signals, from automated metrics and LLM-as-judge ratings to human assessments and benchmark suite results. When these signals are aggregated via averaging, evaluation confidence can then substantially exceed the reliability of the weakest signal: a phenomenon we call trust inflation in evaluation. We argue that evaluation scores should be treated as epistemic claims with thr...

31.07.2026

Blog Dados & Embeddings

OVEarth-Bench: Evaluating Category Breadth and Query Diversity for Open-Vocabulary Earth Observation

arXiv:2607.27278v1 Announce Type: new Abstract: Open-vocabulary Earth observation (EO) aims to localize geospatial concepts specified in natural language rather than a fixed label set. Existing benchmarks, however, usually cover narrow category vocabularies or limited query forms. To fill this gap, we introduce OVEarth-Bench, which extends existing evaluation in two directions: category breadth, through broad hierarchical category coverage with positive and negative expressions, and query divers...

31.07.2026

Blog Dados & Embeddings

DoTime: A Synthetic Benchmark Generator for Interventional and Counterfactual Time Series

arXiv:2607.27263v1 Announce Type: new Abstract: Most benchmarks for causal inference over time series are observational, small, or domain-specific, leaving interventional and counterfactual estimation under-served exactly where it matters most, such as in healthcare, policy evaluation, and climate science. We introduce \textbf{DoTime}, an open, scalable, and theoretically grounded generator of multivariate temporal structural causal models (TSCMs) with interventions, released as the \code{dotime...

31.07.2026

Blog Dados & Embeddings

Private Face Recognition Training Dataset Publication via Identity-Decoupled and Geometry-Preserving Face Distillation

arXiv:2607.27764v1 Announce Type: new Abstract: Publishing private face recognition~(FR) training datasets is privacy-sensitive because faces expose identity information. Private FR training dataset publication mitigates this risk by releasing protected proxies as substitutes for private training faces. However, training FR models with such data introduces an identity paradox: \emph{the identity cues that make released faces useful for recognition supervision are also the cues that make them lin...

31.07.2026

Blog LLMs & Texto

Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance

arXiv:2607.27283v1 Announce Type: new Abstract: Long-horizon benchmarks often show that agents fail more as tasks become longer. This observation is useful for deployment, but it does not by itself explain why failure occurs. More stages create more opportunities for ordinary errors to compound; longer tasks may also contain harder individual decisions or become harder as conversation history, tool outputs, and environment changes accumulate. We use trajectory-induced degradation to mean this la...

31.07.2026

Blog Dados & Embeddings

PlatformBid: An Auto-Bidding Benchmark from a Unified Advertising Platform's Perspective

arXiv:2607.27265v1 Announce Type: new Abstract: Real-time bidding is central to computational advertising, comprising three elements: Supply Side Platform (SSP) selling ad impressions, Demand Side Platform (DSP) bidding for advertisers, and Ad Exchange conducting auctions between them. Traditional auto-bidding algorithms focus solely on the DSP side, maximizing advertiser conversions by adjusting bids against competitors. However, current big ad platforms, such as social media and e-commerce com...

31.07.2026

Blog Dados & Embeddings

Objective-Aligned Direct Answer SFT for Robust Multi-Frame Medical VQA

arXiv:2607.27566v1 Announce Type: new Abstract: Multi-frame medical VQA appears to reward increasingly complex adaptation: controller-style inference, localization-aware reranking, static hard-negative mixing, and staged continuation all appear plausible from first principles. We test a simpler competing hypothesis on MedFrameQA: methods that remain tightly aligned with the benchmark's final answer objective should be the strongest \emph{robust} adaptation family once evaluation is controlled ac...

31.07.2026

Blog LLMs & Texto

From Single- to Cross-Document: Benchmarking Multi-Granularity Event Analysis of Large Language Models

arXiv:2607.27654v1 Announce Type: new Abstract: Event analysis is an essential and fundamental direction of information extraction, involving various event-centric tasks at different granularity of documents. While large language models (LLMs) have preliminarily achieved promising performance in part of these tasks individually, their capability in event analysis still lacks comprehensive understanding due to restricted document granularity, task designs, and data source of existing benchmarks. ...

31.07.2026

Blog Robótica & RL

SemAnCorr: Semantic Anchored Correspondence for Zero-Shot Manipulation Skill Transfer

arXiv:2607.28382v1 Announce Type: new Abstract: Transferring manipulation skills across object instances that share functionality but differ in geometry remains a fundamental challenge in robot learning. While recent correspondence methods leverage dense visual descriptors and 3D feature fields, nearest-neighbor feature matching often produces spatially incoherent correspondences that fail to recover the local geometric frames required for reliable skill transfer. We introduce SemAnCorr, a train...

31.07.2026

Blog Robótica & RL

Good Rankers, Bad Objectives: Bilinear Contrastive Critics under Expressive Policy Search

arXiv:2607.27422v1 Announce Type: new Abstract: Good action rankings do not make a contrastive critic safe to maximize. These critics increasingly act as value-like objectives for best-of-$K$ selection, planning, and critic-guided generation. Unbounded bilinear scores can let large embedding norms inflate off-support values, but cosine bounding does not remove the failure. A controlled support decomposition attributes most raw bilinear regret to norm drift. Cosine and hybrid critics nevertheless...

31.07.2026

Blog Dados & Embeddings

A Lightweight Foundation Model for Collider Physics with Multi-Domain Adaptation

arXiv:2607.27501v1 Announce Type: new Abstract: We present a lightweight approach to foundation modeling (\textbf{NEXUS}) that leverages pre-trained learning from collider physics data towards out-of-domain tasks in other scientific datasets, using a fully connected autoencoder model with approximately 3 million parameters. The model pre-trains with no supervision over a large-scale collision dataset from the Large Hadron Collider modeled by charged particle track features. Downstream tasks for ...

31.07.2026

Blog LLMs & Texto

Gradient-free Task-Conditioned Retrieval for On-Device In-Context Learning

arXiv:2607.27766v1 Announce Type: new Abstract: On-device in-context learning (ICL) relies on pre-inference retrieval to select demonstrations for useful context before downstream model inference. This retrieval must exploit task-specific information while operating over local memories under limited computation, memory, and data-exposure budgets. We propose Conditional Retrieval Alignment (CoRA), a gradient-free framework that converts a frozen encoder into a task-conditioned retriever using pai...

31.07.2026