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…
Sunday 18 October
- PaperCompile Once, Run Cheap: Frozen, Portable Skills for Embodied Agents, and What Recursive Self-Improvement Adds
Embodied AI lacks the data-rich pretraining that gave language models their agents and skills, so new manipulation capability costs demonstrations per task or a frontier
- PaperSelf-organizing reinforcement learning: a learner-free swarm approaches the explore-exploit optimum
The explore/exploit trade-off is the core problem of reinforcement learning (RL). We show that a minimal foraging swarm approaches its optimum - the ideal-free / Nash all
- PaperExplore or Confirm? LLM Agents Misallocate Measurements Under Noise
As model reasoning gets cheaper, the physical experiment becomes the slow and costly step in discovery. Each experiment returns a noisy reading: a high value can mean a g
- PaperGeneration-Heavy Hybrid Machine Translation
The state of the art techniques in Machine Translation (MT) require large amounts of symmetric resources from source and target languages. This is true regardless of whet
- PaperNon-Acceleration of the Heavy-Ball Method in 1D
Despite having an asymptotically optimal rate of convergence on convex quadratics, the acceleration of Polyak's heavy-ball method and a characterization of its dynamics w
- PaperDeep Fusion Memory: A Chunk-Level Parametric Memory for Large Language Models
Large language models need effective ways to acquire and use external knowledge beyond what they retain from pretraining. Continued pretraining risks catastrophic forgett
- PaperPre-Query Retention with Bounded Bit and Word Retrieval
An agent can retain information before receiving a future question and later retrieve evidence from an archive. Evaluating this arrangement requires accounting for both r
- PaperToward Agentic Retrieval-Augmented Generation for Enterprise Retail Workflows over Heterogeneous Data Sources
Enterprise retail workflows require agents to chain evidence across heterogeneous sources, from structured product and order records to unstructured inquiries and reviews
- PaperConformal Prediction-Enabled Sequence-level Policy Optimization for Reasoning Language Models
Reinforcement learning improves the reasoning capability of large language models through verifiable rewards for mathematical and coding tasks. In token-level methods suc
- PaperThink Visually Across Space and Time: Grounded Reasoning for Video Segmentation
Video Reasoning Segmentation (VRS) requires a model to identify an implicitly described target and predict its pixel-level mask trajectory, while resolving the spatial re
- PaperDAGLoop: Aligning Method Design with Experimental Feedback in Automated AI Research
Automated AI research agents aim to improve machine learning methods by iteratively proposing, implementing, and evaluating candidate methods. Existing work uses the outc
- PaperBeyond Factual Accuracy: A Benchmark for Evaluating Perspective Alignment in LLMs
Large Language Models often generate factually correct responses that fail to maintain user-requested perspectives, blending multiple perspectives and forcing users to fi
- PaperDual-Slot: From Serial Loops to Parallel Slots in Language Models
Looped language models increase computational depth by repeatedly applying shared layers, offering a way to improve model quality without adding parameters. However, sequ
- PaperSufficient Frame Subsets for Video Understanding
Understanding when during a video a model makes its critical observations is essential for interpreting video-understanding systems. However, existing attribution methods
- PaperCoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?
Model--harness co-evolution has emerged as a prominent paradigm for recursive self-improving (RSI) agents, jointly evolving their execution scaffolds and intrinsic capabi
- PaperP2N: Reusing Deep Representations for Greater Effective Depth
Mathematical problem solving and autonomous agents are increasingly important applications of language models, demanding stronger reasoning capabilities. Computational de
- PaperMoCKEFA: Model-Conditioned Keyframe Extraction and Fair Attribution for Video Model Explanation
We show that a video can be represented with just a few keyframes without sacrificing a given model's belief about the video. Our method is the first of its kind that ext
- PaperMoWE: Spatially Adaptive Mixture-of-Wavelet-Experts Pooling for Ultrasound Lesion Segmentation
We present Mixture-of-Wavelet-Experts (MoWE), a spatially adaptive routing mechanism that replaces max-pooling and strided convolutions in U-Net architectures for ultraso
- PaperAuto-MD-bench: Evaluating Autoresearch Agents for Real-World Medical Tasks
Autonomous agents are increasingly capable of developing machine learning (ML) models end to end. In medical practice, however, strong performance on the target metric do
- PaperLocalization and Neural Splatting on the Edge: An FPGA Scene Memory for Robots
Resource-constrained robots and autonomous vehicles need scene memories that localize a camera and render nearby views without a desktop GPU. Scene-coordinate regression
- PaperOne Skill Takes Over: Clashing Agent Skills and a One-File Fix
Agent Skills are instruction files that tell a coding agent how to do one job. Users install skills from many authors, so two skills for the same job can be active at the
- PaperLightCRS: Lightweight Multi-Domain Conversational Recommendation System
Conversational recommender systems have recently adopted vision-language models to match user dialogue intents with multimodal product information. However, extending the
- PaperThe Optimal Sample Complexity of Pointwise Replicable Agnostic Learning
Pointwise replicability asks that two independently trained predictors, using the same random seed, agree at each fixed query with high probability. We determine its opti
- PaperPolicy Is Not Capability: Some Safety Benchmarks Measure Which Definition of "Unsafe" You Trained On
A guardrail classifier is reported as if unsafe were a property of text. It is not: it is a property of a policy, and the policy enters the model through its labels. We e
- PaperHCFM: Helmholtz Component Flow Matching for Time Series Anomaly Detection
Flow Matching (FM) is an efficient simulation-free approach for training flow-based generative models, making it a promising foundation for scalable time-series anomaly d
- PaperPRET is a few-shot system for pan-cancer recognition without example training
Pathological examination stands as the cornerstone in cancer diagnosis, impacting millions worldwide annually. With the shortage of pathologists globally, artificial inte
- PaperPACT: NVFP4 Data-Flow LoRA Fine-Tuning on Consumer GPUs
Fine-tuning language models on consumer GPUs is constrained by computation and memory. Although LoRA reduces trainable parameters and optimizer state, frozen projections
- PaperSteadyThought: Mitigating LLM Under-Thinking via Thought-Level Preference Optimization
Flexible switching between reasoning trajectories (i.e., thought switching) has significantly enhanced the reasoning capabilities of Large Reasoning Models (LRMs). Howeve
- PaperNormalizing Flow for Neural-Enhanced Track-Before-Detect
Multiobject tracking (MOT) is a fundamental capability in autonomous navigation, radar and sonar systems, as well as 6G integrated sensing-and-communication (ISAC) networ
- PaperVLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse
Flow-matching vision-language-action (VLA) models generate an action chunk by iteratively denoising Gaussian noise, but typically execute only a short prefix before repla
- PaperBeyond the Teacher: Understanding and Preserving Distillation Overshoot in Agentic On-Policy Distillation
On-policy distillation (OPD) trains agents on their own trajectories using supervision from a stronger teacher. We uncover a counterintuitive phenomenon in multi-turn age
- PaperOne Head Away from Language Confusion: Single Attention Heads Across Model Families
Large language models sometimes reply in an unexpected language, a failure known as language confusion. We ablate individual attention heads in 12 model checkpoints spann
- PaperQuadratic Sample Complexity for Strictly Replicable Realizable Learning with Unknown Marginals
Under the quantifier $\exists A\,\forall D$, where the realizable distribution and its marginal are unknown, we determine the finite-class sample-complexity exponent for
- PaperIntegrable building blocks for symplectic neural networks: learned-type layers, fiber-preserving layers, and what a single layer can do
Exactly symplectic neural networks are built almost exclusively from shear maps and gain expressivity only through depth. We ask what else a single explicit symplectic la
- PaperSynergy-Aware Residual Flow Matching for Single-Cell Perturbation Prediction
Predicting single-cell responses to genetic and chemical perturbations is important for understanding regulatory mechanisms and prioritizing therapeutic interventions. Ex
- PaperLLM Agents as Suppliers of Physical System Models: Calibration and Acceptance in Modelica
To procure a model of a device, a client hands a supplier a description, sometimes with recorded data or a target response, and accepts the model against this handover. W
- PaperDecentralized Online Exp-Concave Optimization
Decentralized Online Convex Optimization (D-OCO) is a fundamental framework in which a set of local agents aims to minimize a sequence of global loss functions using only
- PaperMultifidelity Monte Carlo Estimator for High-Dimensional Quantities of Interest
Multifidelity Monte Carlo (MFMC) reduces the cost of estimating the statistics of quantities of interest (QoIs) computed via expensive high-fidelity model by using cheape
- PaperIECLA: Interpretable Emotion Contribution Learning for Affective Image Editing
Affective image editing (AIE) aims to evoke a target emotion while preserving the content and structure of a source image. Existing methods improve emotional expression o
- PaperLatent World Models Should Plan with Distances Along the Latent Manifold
Latent world models such as LeWM plan by searching for an action sequence whose predicted terminal latent is closest to the goal latent under an ambient norm, such as the
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.