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…
Monday 19 October
- PaperPolar Switch: Fast Muon Orthogonalization with Polynomial Circuits
Muon, a 2024-born optimizer for language models, differs from the 2015-born spectral gradient descent mainly in its fast, GPU-friendly Newton--Schulz polynomial for ortho
- PaperCheckDistill: Adaptive Checklist Distillation for Efficient Distributional Reward Modeling in Image Editing
Reinforcement learning for instruction-guided image editing requires reward models that provide reliable, accurate, and efficient feedback. Direct scalar prediction compr
- PaperCAVA: Complementary-Label-Aware Data Valuation
Complementary-label learning (CLL) trains a classifier from labels that name a class an instance does not belong to. Such labels are cheap to collect from crowdworkers or
- PaperCross-Fitting for Neural Posterior Estimation
Neural Posterior Estimation (NPE) fits an amortized conditional density estimator to a simulated training set of complete-data realizations. NPE's training objective, log
- PaperEpiLens: Lightweight RAG for Epidemiological Knowledge Acquisition
To prepare for future outbreaks, researchers need to know what studies have been done and what data they use. Mapping a large literature by hand is slow, while large lang
- PaperPlanarCityLoc: Breaking Silhouette Ambiguity in LoD Aerial Localization via 3D Planes
Aerial visual localization is crucial for autonomous drone navigation in urban environments where GNSS signals are often degraded. Lightweight textureless Level-of-Detail
- PaperFluent but Fallible: Benchmarking Hallucination and Factual Reliability in Large Language Models
Large Language Models (LLMs) have significantly advanced natural language processing and artificial intelligence applications through their capabilities in reasoning, tex
- PaperInjection of Space Radiation Errors on Low-power NVM using Generative Deep Learning
We develop an error model for a Non-Volatile Memory (NVM) device that represents the effects of physical faults experienced in a CubeSat mission in Low Earth Orbit (LEO).
- PaperCopying Under Repetition: From Prefix Matching to Position Hashing
Frontier LLMs can copy random text almost flawlessly, yet they often overrun or truncate long blocks of repeated characters. In repeated strings, matching local content n
- PaperA Flexible ROI Analysis Tool for Spatially Consistent Vegetation Index Extraction from Turfgrass Imagery
Time-series multispectral imaging is widely used to assess turfgrass condition; however, extracting plot-level vegetation index (VI) values remains labor-intensive when c
- PaperDeep Pontryagin Learning for Continuous-Time Stochastic Control with Jumps
We develop a deep Pontryagin learning framework for high-dimensional continuous-time stochastic control problems that naturally accommodates jump-diffusions. In contrast
- PaperHoloCosm: Beyond Single-Metric Benchmark Compression Across Multiple Metrics
Benchmark compression reduces evaluation cost by selecting a small set of samples. Existing methods typically guide selection using a single metric, although benchmarks o
- PaperPVBench: Quantifying Physical Plausibility in Video Generation with Object-Level Physical Measurements
Recent video generation models produce visually compelling outputs, yet their physical plausibility remains poorly measured. Physical plausibility asks whether generated
- PaperDoubly Robust Learning of Heterogeneous Survival Treatment Effects under Time-Varying Treatments
Estimating heterogeneous survival treatment effects (HSTEs) from time-to-event data under time-varying treatments is important in fields such as medicine (e.g., to decide
- PaperGeoSplit: Selective Edge--Server Map Acquisition for Cross-User Travel-Mode Recognition
Networked mobility sensing couples local trajectory inference with remote geospatial context, making communication decisions part of the prediction system. We present Geo
- PaperTowards Robust Model Organisms for Eliciting Latent Knowledge
A key problem in AI safety is eliciting latent knowledge (ELK), extracting information from a model that is misaligned and more knowledgeable than its overseer. For examp
- PaperHierarchical Token Merging with Recursive Autoencoders for Unsupervised Grammar Induction
Hierarchical abstraction is a fundamental principle across many data modalities, enabling complex sequences to be represented compositionally at multiple levels. Learning
- PaperParallel Language Models via Variational Decoding
Autoregressive language models emit one token per forward pass. This causes high inference latency, in particular as models are scaled up for quality. In this paper, we i
- PaperFoundation Model Driven Optical Flow
We investigate how frozen pretrained visual and depth representations support dense optical flow when coupled with a supervised matching network. Building on TTSFlow, thi
- PaperIntra-Rubric Reward Divergence: Mitigating Rubric Hacking through Latent Dimension Recovery and Balancing
Rubric hacking limits both performance and training robustness in rubric-based reinforcement learning. By decomposing rubrics into sub-dimensions, we reveal the Intra-Rub
- PaperM-Plan: Comprehensive Planning For LLM Agents with Memory Arrangement
Large language model (LLM)-based agents have recently demonstrated outstanding performance in single-turn tasks, yet they continue to struggle with long-horizon tasks, pa
- PaperBrushOff: Stroke-Based Re-rendering as a Watermark Removal Attack on Painting
Invisible watermarks are used to mark who owns a painting. We show that a simple attack removes the most robust one we test. The attack redraws the watermarked painting w
- PaperFrom Short Clips to Real-Time Streams: Identity-Aware Supervision and Context-Efficient Generation for Video Face Swapping
Video face swapping transfers the reference identity to a target video while preserving its other attributes and motion. Despite recent progress in reference-guided flow-
- PaperStepBench: Diagnosing Real-World Procedural Understanding in AI Agents
Evaluating an agent's planning ability remains challenging for open-domain tasks, where verifying procedures through execution is often impractical. Existing evaluations
- PaperWhich Model for Which Role? Cost-Efficient Pareto Recommendation for LLM Agentic Workflows
LLM agentic workflows increasingly employ different models for specialized roles. Users may prefer different trade-offs between task quality and deployment cost, sometime
- PaperPACT: Plan-Augmented Coordination via Trace-Graphs for Dynamic Multi-Agent Combinatorial Optimization
Multi-agent approaches have been investigated recently as a means of improving the scalability of reinforcement learning for neural combinatorial optimization. Existing m
- PaperNested Shared-Operator Recursion on ARC-AGI-1: An Empirical Study of HRM, TRM and URM
Recursive reasoning models refine persistent internal states by repeatedly applying learned operators. We investigate whether adding a persistent intermediate state that
- PaperHoneypots for AI Agent Insider Threats
AI agents deployed inside organizations can pose an insider threat if they make mistakes, are compromised by an attacker, or pursue misaligned objectives. We propose hone
- PaperCaptionFuse: Training-Free Composed Product Retrieval Via VLM Intent Captioning and Weighted Embedding Fusion
Composed Image Retrieval (CIR) retrieves products matching a reference image modified by natural language---a core capability for eCommerce search. Existing training-free
- PaperAllPath: Layered Verification for a Deployed, Self-Revising LLM Trading Agent under Human-Gated and Autonomous Regimes
LLM trading agents are evaluated almost exclusively in backtests and autonomous benchmark harnesses. Deployment, where actions are irreversible, raises a different questi
- PaperTandem: Serving Hybrid Linear-Attention GUI Agents on Mobile NPUs
Smartphone GUI agents complete tasks in mobile apps by repeatedly reading the screen and asking a model for the next action. Mobile neural processing units (NPUs) enable
- PaperSpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?
Spatial intelligence requires agents to actively acquire visual evidence and integrate observations into a coherent representation of the three-dimensional world. Yet spa
- PaperThe Development of Sycophancy in Language Models: Tracing Vulnerabilities from Pretraining to Post-Training
Language models can change a committed answer to accommodate a user's opinion or pushback without new evidence. However, when this behaviour develops during training and
- PaperThe Effectiveness and Durability of Pretraining Data Filtering in Protein Language Models
Pretraining filtering is one of the most common safeguards for open-weight language models. Here we study its effectiveness, durability and scalability using the ESM-2 fa
- PaperFrom Outcomes to Components: A Counterfactual Evaluation Framework for LLM-Proposed Repairs
A repair action proposed by a large language model (LLM) specifies which records to change and how to change their values. A failed action may still contain a useful choi
- PaperReasoning-Aware Multicalibrated Reliability Predictors for Language Models
As people increasingly rely on large language models (LLMs) for information, model providers need to communicate meaningful estimates of whether individual responses are
- PaperDual-Scale Condition-Shift Editing for Robust Real-World Image Demoiréing
Robust demoiréing of screen-recaptured images remains challenging: moiré varies in frequency, color, and spatial support across display-camera pairs and capture condition
- PaperRevision-Based Learning from Interactive Experience and Feedback
Code generation models are increasingly used to produce interactive artifacts, such as websites and user interfaces. Many properties that determine whether these interfac
- PaperWhen the harness decides success: state that cannot be re-observed
Agent harnesses decide what a language model sees across turns: they drop old turns, summarize them, or replay the model's own earlier reasoning. We ask when these choice
- PaperVaDar: Implicit Goal Conditioning via Value Disaggregation
Long-horizon tasks are important for modern AI and robotics, yet pose a challenge for reinforcement learning. Historically, a popular approach has been to decompose a tas
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.