New
Everything new in AI as it appears: launches announced by the labs, brand-new models, datasets, papers and open-source tools. Checked every minute or two. Launches feed · Trending · News
Live now
- Connecting…
Thursday 15 October
- PaperCan LLMs predict the outcomes of machine learning experiments?
Recent advances in AI make Recursive Self-Improvement (RSI) increasingly plausible. Large Language Models (LLMs) can already propose, select, and run Machine Learning (ML
- PaperBroad and Efficient PII Detection with Unified Labels
Personally Identifiable Information (PII) detection models must efficiently find identifiers across diverse contexts while maintaining a low false-positive rate (FPR) on
- PaperWeakly Supervised Discovery of Motion Styles for Compositional Robot Control
When a robot possesses more degrees of freedom than a task requires, multiple trajectories can achieve the same objective using distinct motion styles. Compositional robo
- PaperDiagnosing GNN Failure Modes with Layer-Wise Probe Entropy
Graph neural networks (GNNs) are typically evaluated only at their final layer, obscuring how task-relevant information evolves during message passing. We introduce a pos
- PaperThe Model Knows Better: Defending Medical Multi-Agent Systems Against Prompt Injection
Medical multi-agent systems, in which LLM agents discuss a case, are increasingly studied for clinical decision support. Prompt injection, text that an attacker adds to a
- PaperFlat Loss, Evolving Features: Grokking in Modular Addition
Can a network keep learning while its training cross-entropy stays nearly flat at a positive level? We show that it can. On modular addition, a standard testbed for grokk
- PaperSAG2: Embedding-Free Multi-Hop Retrieval with BM25 and JEV
Strong multi-hop retrieval should be practical to deploy without expensive corpus preparation or complex database infrastructure. We present SAG2, an embedding-free retri
- PaperMitigating Demographic Disparities in Explanation-Human Alignment via Rationale Regularization
We study explanation fairness in hate speech detection. High classification performance does not always mean that a model produces equally plausible explanations for diff
- PaperInitiating Removal from Operational Symptoms in Federated Vehicular Networks
Connected vehicles train a driving model through federated learning (FL) and drive with it, so a faulty contribution often surfaces only as a delayed symptom on the road.
- PaperNoise-Robust Forced Alignment for Spontaneous Speech
We show that forced aligners degrade on spontaneous, noisy real-world speech, and that fillers, laughter, and disfluencies corrupt word boundaries, impacting many downstr
- PaperEmbodiment-Classifier Guidance: Transferring Frozen VLAs Across Robot Dynamics without Demonstrations
Flow-based policies such as $π_0$ are trained on a fixed set of embodiments, and transferring them to new ones is an open problem. To adapt a frozen $π_0$ to a new embodi
- PaperStructure-Aware Spatial Kernels for Gaussian Process Distributed Port-Hamiltonian Systems
Gaussian process distributed port-Hamiltonian systems (GP-dPHS) enable data-driven modeling of distributed dynamical systems while preserving their physical structure. Ho
- PaperAlignment of visual brain encoding models with individual perceptual similarity judgments
Encoding models that predict brain activation responses to images have traditionally been trained to maximize accuracy when predicting observed brain data. However, their
- PaperRepairing LLM-Generated Specifications with Deterministic Diagnosis
Large language models (LLMs) are increasingly used as formalizers: given a reasoning problem expressed in natural language, they produce a formal specification that a sym
- PaperWho Do Perspectivist Models Predict Well? Annotator Agreement, Sparsity, and Performance
Successful completion of perspectivist natural language processing (NLP) annotation tasks requires algorithms to be aligned across diverse perspectives in order to predic
- PaperSeeing Seizures: A Large-Scale Empirical Study of Video and EEG Deep Learning for Automated Rodent Seizure Detection and Severity Grading
Manual annotation of synchronized video and EEG recordings is a bottleneck in preclinical seizure research. We present an empirical study of seizure detection and behavio
- PaperCoverage Cliffs in Off-Policy Quantile Certification
We study when logged contextual-bandit data can certify an upper tail quantile for a policy selected from the same sample. We construct a PAC-Bayes Bernstein lower-confid
- PaperDeterministic Bounds on Accuracy and Stability of Metric-Space Regression and Classification
Data-driven approaches often face ambiguity in datasets due to sensor or target noise, insufficient information, and noise in the input data. While best-fit machine learn
- PaperMicro-Localization: High-Precision Mobile Robot Localization Using Microscopic Ground Texture
We demonstrate high-precision global localization using natural ground texture viewed through microscope optics, achieving localization in the tens-of-micrometers regime.
- PaperFRACTAL: A Self-Similar Multi-Agent Orchestration Architecture with Formal Communication, Convergence, and Depth Bounds
We present FRACTAL, a self-similar multi-agent architecture for recursive goal decomposition, in which the same five-component organizational pattern -- Orchestrator, Ens
- PaperWhen Plans Change, Remember: Replanning-Guided Visual Memory for Vision-Language-Action Models
Long-horizon, multi-stage Vision-Language-Action (VLA) policies often require visual information that is no longer present in the current observation. Retaining the compl
- PaperGenerative AI Produces and Transmits Beauty Bias
Societies reward people judged to be attractive by standards intertwined with gender and race. In this paper, we examine if and how generative AI may contribute to these
- PaperCFC26: Building Evaluations for Deployment in Sonar-Based Fish Counting
Accurate counts of fish populations are essential for monitoring ecosystems and making decisions for conservation, harvest limits, and river management. In many field dep
- PaperCultural (In)Competence: Investigating Culture-Specific Stereotype Detection Capabilities of LLMs
Stereotypes are subjective constructs that are mediated by the cultural context in which they are viewed. Successfully modeling them thus also requires cultural competenc
- PaperOn the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction
Diffusion language models (DLMs) promise parallel text generation, but in practice face an unresolved speed-quality trade-off. Exact decoding fills in only one masked pos
- PaperHeRE: A Novel Benchmark for Hebrew Relation Extraction via LLM-Guided Denoising of Knowledge Graph Alignments
While LLMs demonstrate strong capabilities in English Relation Extraction (RE) tasks, a significant gap remains in assessing their RE performance in low-resource language
- PaperDon't Retrain, Remix: Adaptation of Web Agents using Mixture Hypernetworks
The web is not static or uniform. Websites that serve the same purpose can look and navigate very differently. Even within a single site, successive redesigns can change
- PaperAre Large Reasoning Models Good Everyday Reasoners? A Comparison with Non-Reasoning Models on Logical Reasoning Tasks
Large reasoning models (LRMs) that leverage test-time computation achieve strong performance on mathematical and scientific benchmarks and are increasingly deployed in re
- PaperFlashControl: One-Step Controllable Generator via Distillation-Friendly Single-Stream Teachers
Diffusion models have become a leading approach in visual generative modeling, particularly effective in text-to-image and controllable generation. Their main drawback is
- PaperPearl-Chat: Engineering a native Luganda language model from first principles in JAX and Flax NNX
Autoregressive foundation language models predominantly target high-resource Indo-European languages, imposing computational and morphological penalties on under-represen
- PaperLiteral Lock-In: How Test Language Shifts Literal Attraction in Typed Decision Models on Bengali Idioms
Decision models, non-generative scorers that report a probability over caller-supplied options and emit no text, are increasingly deployed as routers, classifiers and gua
- Paperalkhder at AlexandriaX-2026: Context-Aware English-to-Dialectal Arabic Dialogue Translation with QLoRA-Fine-Tuned NileChat-3B
This paper describes team Alkhder's submission to Subtask 1 of the AlexandriaX-2026 shared task, which asks systems to translate English dialogue turns into thirteen Arab
- PaperLearning the Shared Latent Structure of Cryo-EM Inverse Problems
Understanding biomolecular function requires characterizing three-dimensional structure and conformational variability, for which cryogenic electron microscopy (cryo-EM)
- PaperLearning smooth dynamics via Kinematic Interpolants
Inferring dynamics from real-world experimental data is inherently ambiguous, as many plausible dynamical systems can explain the same positional observations at measurem
- PaperLearning User Representations to Improve Simulation Fidelity
User simulators enable interactive training and evaluation of AI assistants at scale. Yet current simulators struggle to reproduce the diverse behaviors of real users, le
- PaperSource-Aware Dynamic Pricing with Strategic Buyers
In modern commerce, firms and platforms typically use customer features from different sources to personalize prices: some features are verified using seller records or t
- Paperalkhder at ImageEval 2026 Shared Tasks: Constrained Selection and Rotation-Averaged Logit Scoring for Multimodal Hallucination Detection
We describe our submission to Subtask~1b of ImageEval 2026. The task consists of selecting the single visually valid statement from three candidates paired with an image,
- PaperTowards Reconstructing Geographically Diverse Architecture with 3D Foundation Models
Internet-scale photo collections of real-world landmarks have driven progress in 3D computer vision yet remain highly challenging for modern 3D foundation models (3DFMs)
- PaperPredicting Privileged Information Effectiveness for On-Policy Self-Distillation
On-policy self-distillation (OPSD) enables large language models (LLMs) to learn from privileged information (PI) without a separate teacher model. However, prior work la
- PaperAuditKIT: A Unified Evaluation Spine for Benchmarking, Judging, and Comparing Large Language Models and Agentic Systems
Evaluating language models and agents requires combining benchmark accuracy, judge-based assessment, runtime performance, tool-use behavior, and retrieval quality. Differ
Headlines and links come from the labs' own blogs, Hacker News and the GDELT news index, and from the sources our index already follows. We show a short excerpt and always link to the original. A launch reported by a news site rather than the lab is marked “Reported” until the lab itself announces it.