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
- PaperOV-PEAR: Observation-Verified Pose-Scale Estimation and Reconstruction for Unknown Industrial Manipulation Objects
Fine industrial robotic manipulation requires 6D pose, scale, and an operation-ready 3D model. Existing industrial pose estimation relies on CAD models, object-specific t
- PaperWhere RL Breaks: Localizing and Repairing Failures via Targeted Continued Pretraining
Reinforcement learning with verifiable rewards (RLVR) is widely used to improve reasoning in language models, yet growing evidence suggests that it mostly sharpens what t
- PaperDiffusion Language Models Change Speed Across Tasks and Languages
Diffusion language models can write several tokens in one forward pass, and they decide during generation how many passes to spend. Two outputs of the same token length c
- PaperFrontierRefactor: Benchmarking Multi-Scale Performance-Oriented Codebase Refactoring
Autonomous codebase refactoring requires coding agents to restructure working software while strictly preserving externally observable behavior and prioritizing execution
- PaperHihaze: One-Step Diffusion for High-Resolution Real-World Image Dehazing
Diffusion models have recently achieved encouraging results in real-world image dehazing. However, restoring high-resolution images remains challenging due to spatially n
- PaperWhen Retrieval Partially Conflicts with Skills: Understanding Procedural Hallucination in Language Models
Language models increasingly use skills that provide reusable instructions and procedures for task execution. After a relevant skill has been selected, the model may need
- PaperOptimizing Marketing Budgets for Social Influence: A Generalized Fractional Incentives Framework
Marketing managers routinely allocate limited budgets across individuals in social networks whose responsiveness and influence vary substantially. We study the problem of
- PaperWhen to Stop Asking: Factor Coverage Bias and LLM Determinability Judgments with Underspecified Information in Medicine
Clinical decision-making often begins with underspecified information and requires not only gathering missing information but also knowing when to stop. This calls for ju
- PaperModal Sense Disambiguation in Language Models: The Role of Context, Training Domain, and Input Frequency
Modals such as may and must can take on different senses depending on discourse context, alternating between root interpretations (e.g., permission, obligation) and epist
- PaperDynamic Dual-Feedback Conformal Inference for Time Series Forecasting
Quantifying uncertainty in time series forecasting is particularly demanding because sequential data exhibit temporal dependence and are prone to distributional changes.
- PaperIs it RL or Data? A Controlled Comparison of GRPO and Rejection-Sampling Fine-Tuning
Bauer et al. (2026) showed that in low-data reinforcement learning with verifiable rewards, training GRPO on mixed-difficulty prompts gives up to 5x the sample efficiency
- PaperWhen Stable and Preferred Semantics Agree: A Path-Based Approach
We investigate structural conditions under which preferred and stable semantics agree in abstract argumentation frameworks. Our approach is based on suitably chosen sets
- PaperCommunication-Efficient Federated Domain Generalization in Edge Networks via Dynamic Prototype Regulation
Federated learning (FL) is a distributed paradigm for Internet of Things (IoT) edge networks. However, deploying Vision-Language Models (VLMs) over wireless edge networks
- PaperDo We Need Learned Targets? Classical Gradients as Supervision for 2D Gaussian Initialization
Learning-based Gaussian image initializers can require costly supervision obtained by per-image optimization. We investigate whether the Pseudo-PPM targets used by Instan
- PaperSector-Ring Linear Reservoirs: Sector-Wise Decay-Timescale Allocation With State Reuse Across Candidate Settings
In reservoir computing, performance depends on whether the fixed dynamics of the reservoir suit the task, and the appropriate memory length and frequency response differ
- PaperThink Before You Transcribe: Context-Steered Reasoning for Hotword-Aware Speech Recognition
Contextual automatic speech recognition (ASR) improves rare-entity recognition by supplying candidate hotwords, but retrieved candidates may be incomplete or incorrect. A
- PaperAirMPA: A Meteorology-to-Pollution Adapter for Global Air Quality Forecasting
Accurate real-time forecasting of atmospheric pollutants is essential for reducing exposure risks and improving public health. Traditional numerical forecasting systems s
- PaperFair Regression under Approximate Demographic Parity
Exact demographic parity requires the same prediction distribution across sensitive groups. In regression, this can be too restrictive and reduce predictive accuracy. We
- PaperSAR: Learning Global Item-Space Matching and Geometry-Aware Placement Ranking for Buffered Online 3D Bin Packing
Online 3D bin packing with a bounded buffer requires irreversible item-selection and placement decisions under limited knowledge of future arrivals. Feasibility alone is
- PaperCoMem: Learning to Anticipate Failures from Retrieved Experience
Reflection lets LLM agents improve from their own attempts, but the memory it builds is local to a single task, so an agent reflecting on its own tends to revisit the sam
- PaperCan LLM User-Proxies Stand In for Humans in Reliance Measurement? Replicating Rel-A.I. with Simulated Users
Can language-model user proxies reproduce human reliance on an AI answer across contexts? Published simulated-user studies do not establish validity for this partial-answ
- PaperUniJev: Separating Accuracy from Calibration in Trimodal System One Decision Models
System One models produce probabilistic judgments that software can consume directly, making reliable confidence as important as answer accuracy. Yet joint training acros
- PaperSee the Future, Classify the Present: Stochastic Latent World Modeling for Hyperspectral Images
Hyperspectral image classification (HSIC) relies on static spatial-spectral representations learned from labeled samples, limiting its ability to model structured depende
- PaperDetection Augmented Learning In Non-Stationary Bandit Environments
We study the problem of non-stationary bandits without knowledge of the environmental changes. We propose Detection Augmented Learning (DAL) a black-box paradigm that com
- PaperOpenSaC: A Python Library for Search as Code in Deep Research Agents
Deep research agents investigate complex questions through iterative search, source examination, and evidence synthesis. A conventional workflow alternates reasoning with
- PaperStanding on the Shoulders of Giants: Enhancing LLM Agents for Automated Fact-Checking with Human Expert Skills
Automated fact-checking (AFC) systems powered by large language model (LLM) agents still face challenges in evidence retrieval and claim verification. Existing approaches
- PaperFrom Trace to Fix: Residual Task State in Long-Horizon Agents
Recovering from failures in long-horizon, stateful language agents is challenging because the action introducing a defect, the symptom exposing it, and the persistent sta
- PaperVHA: VQA-based Hallucination Assessment for Generative Image Super-Resolution
Generative image super-resolution produces visually realistic high-resolution images, but may also introduce hallucinations by adding unsupported content or altering exis
- PaperTruncated Reasoning Under a Budget: Evaluating System-1 Models as Decision-makers
Large language models (LLMs) often generate more reasoning tokens than needed. Limiting the reasoning budget reduces cost, but forcing an answer from an incomplete trace
- PaperEvalRx: Agentic Diagnosis and Verified Repair of Foundation Models
Model evaluation reveals where models fail, but rarely why or whether a proposed fix genuinely works. We introduce EvalRx, an open-source agentic framework for statistica
- PaperTRACE: Tracking Multimodal Clinical Trajectories for Inpatient Risk Prediction
Accurate inpatient risk prediction requires modeling heterogeneous clinical evidence that accumulates irregularly over time. This challenge spans in-hospital mortality, p
- PaperActTime: Action-Conditioned World Modeling for Time Series
Time-series models increasingly condition on known future inputs. In controlled systems, some of these inputs are actions that can be changed, compared, and optimized bef
- PaperComputation, Not Memory: Chain-of-Thought and State Tracking in LLM Agents
Language-model agents often reason before they act, and the value of monitoring that reasoning depends on how it relates to their actions. We ask how an agent's actions d
- PaperRemember Less, Adapt Longer: Bounded-State In-Context Reinforcement Learning with Recurrent Summary Memory
In-context reinforcement learning (ICRL) enables agents to adapt to new tasks without parameter updates, relying on memory to retain what they learn from experience. For
- PaperWhich Answers Agree? Evaluating Self-Consistency from Incomplete Logs
Self-consistency answers a question by generating multiple responses and selecting the most frequent answer. Its evaluation requires both correctness labels and informati
- PaperNADS: Navigator-Guided Data Selection for Mitigating Catastrophic Forgetting in Fine-Tuning
Catastrophic forgetting is a central obstacle in single-stage fine-tuning of large language models (LLMs) on a new task, especially when the original pretraining data are
- PaperCognitively Decoupled Meta-Induction for Out-of-Distribution Generalization
In-context learning (ICL) tackles downstream tasks conditioned on demonstrations. This paradigm relies heavily on neighbor-based matching between queries and demonstratio
- PaperMAPS: A Multi-Agent Personalized Script-Driven Video Advertising System Enhanced by Reinforcement Learning
With the rapid growth of online video consumption, video advertising has become a dominant component of digital advertising. Most personalized video advertising systems f
- PaperBayesian Model Discovery with Language Models: Closing the Loop between Hypotheses and Experiments
Scientific model discovery requires proposing candidate models of an unknown system and designing experiments that discriminate among them. However, LLM-based approaches
- PaperFundamental Limits of Information-Theoretic Secure Aggregation with User Dropouts in Federated Learning
Secure aggregation enables a server to compute the sum of users' gradients or model updates without revealing individual values. With user dropouts, correlated random key
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.