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
- PaperHoli-World: Building Holistic World Intelligence from Human-Ego Experience
Human egocentric experience offers a rich foundation for learning how the world is organized and how it changes through interaction. Realizing this potential at scale req
- PaperAgentic Orchestration of EDC Data Space Retrieval and Natural Language Driven Data Processing
Participating in a data space still requires the Dataspace Protocol (DSP) negotiation flow to be hand-coded against each provider's access policy. We present a multi-agen
- PaperDoes Multi-Agent Collaboration Reduce Hallucination in Clinical Tasks?
Multi-agent LLM systems improve performance on clinical tasks, and that improvement is often read as evidence of a more trustworthy system. However, the two are not the s
- PaperBreaking Diffusion: Parallel Reasoning with Draft Refinement
Drafting an answer allows a reasoning model to reconsider each decision in the context of the others. Yet repeated diffusion denoising does not ensure that individually p
- PaperBR-MoE: Budgeted Semantic Release for Privacy-Preserving Traffic Analytics
Traffic cameras support useful analysis, but their outputs can reveal private information. Replacing images with text reduces direct visual exposure. It does not place a
- PaperSmall Average Error, Wide Individual Error: General-Purpose LLMs Estimating Energy Intake from Meal Photos in a Feeding Trial
Photo-based estimation of food energy could ease dietary assessment, and general-purpose multimodal large language models (LLMs) make such estimates easy to obtain. Most
- PaperReAnchor: Reusing Rejected Verifier States for Diffusion Drafting
Block diffusion drafters accelerate speculative decoding by generating multiple draft tokens in a single forward pass. However, each pass produces only a fixed-length blo
- PaperA Semantic Knowledge Graph Construction Pipeline for Vehicle Intention Prediction in nuScenes
Knowledge graphs (KGs) are increasingly used in autonomous driving (AD) to make traffic scene entities and relations explicit for prediction and reasoning. Existing traff
- PaperA Fisher-Geometric View of Multi-Teacher On-Policy Distillation
Consolidating specialized foundation models into a unified generalist is a central goal of post-training. Two approaches are in common use: model merging, which is fast b
- PaperBeyond Behavioral Accuracy: Evaluating Individual-Level Fidelity in LLM Investor Simulation
Large language models (LLMs) are increasingly used as user simulators, but can they faithfully reproduce an individual's behavior and decision logic over time? We investi
- PaperInterpretable Face Contrast Modeling for Smartphone Portrait Rendering
The quality of smartphone portrait photography has become increasingly important to both manufacturers and users. Recent devices use complex computational pipelines to im
- PaperToward Structured Financial Foundation Models
Foundation models promise reusable capabilities and step-change performance gains across tasks. In finance, large-scale pretraining of domain-specialized foundation model
- PaperRouterWorld: Scaling Conversational AI with Latency-Aware LLM Routing
Conversational AI systems built on Large Language Models (LLMs) require routing mechanisms that balance answer quality and response latency at scale. However, existing LL
- PaperLearn the Task, Not the Schedule: Reducing Spurious Cross-Arm Coupling in Bimanual Imitation Learning
A bimanual demonstration specifies both what the robot should do and one particular schedule for when each arm should act. Standard imitation learning does not distinguis
- PaperScopeMem: Latent Memory That Learns Where to Revise Frozen GUI Agents
Latent memory is gaining ground as a lightweight history supplement for GUI agents. It supplies history to a frozen vision-language model via prefix vectors trained with
- PaperMitigating Reward Hacking in Preference Reward Models with Evolving Penalties
Reinforcement learning for language models has moved from preference reward models to verifiable rewards, which sustain much longer optimization. Preference models are pr
- PaperPDNet: Exploring Pruning and Distillation for Real-Time Worker Activity Recognition in Industrial Assembly
In this work, we address real-time fine-grained human activity recognition (HAR) in industrial assembly and introduce PDNet, a new framework that jointly exploits structu
- PaperStrength Controls Change How Interventions Compare Across Sparse Autoencoder Codes
Changing sparse autoencoder (SAE) codes can alter both intervention direction and magnitude, so comparing intervention effects requires a strength control specifying what
- PaperSPAR: Structural Pruning and Action Recovery for Vision-Language-Action Models
The limited onboard computing resources of robots make the inference demands of vision-language-action (VLA) models costly to accommodate. Reducing these demands through
- PaperWet-Biased Data Pipelines Mislead the Training and Evaluation of Generative Precipitation Nowcasting
Generative models for precipitation nowcasting are trained and evaluated predominantly on wet-biased datasets, which over-represent precipitation events to emphasize rare
- PaperGaussian Approximation of Besov Functions for Logistic Classification on Manifolds
We study Gaussian kernel approximation and regularized logistic classification on a connected compact smooth embedded manifold $X\subset\mathbb R^d$ without boundary and
- Paper3D Diffusion Models for Medical Imaging
Generative deep learning methods such as Variational Autoencoders, Generative Adversarial Networks or Diffusion Models have achieved remarkable results in image synthesis
- PaperAfriGuard: Safety and Robust Refusal For African Languages
Large language models (LLMs) designed to interact with users are typically trained to respond appropriately to harmful or toxic content. However, ensuring appropriate res
- PaperA Simple and Unified Method for Gradient-Variation Regret
Gradient-variation online learning has attracted increasing attention for its connections to game theory and optimization. It has been studied in both non-stationary onli
- PaperOn Learning Expand-and-Sparsify Representations
Expand-and-sparsify ($\texttt{EaS}$) representations lift an input to a much higher dimension through a linear map and keep only the $k$ largest coordinates. Existing the
- PaperVeriCUA: Learning Proactive Verification for Reliable GUI Agent Rewards
Reinforcement learning for computer-use agents increasingly relies on proactive reward agents that interact with the post-execution GUI environment to verify what recorde
- PaperYUTELA: A Scalable Edge Cloud AIoT System for Multi-Site Video Anomaly Detection with Scene Specific Adaptation
Building upon our previous Ancilia framework, this work presents \emph{YUTELA}, an edge--server--cloud AIoT system for long-term, multi-site video anomaly detection. YUTE
- PaperTraining Negatives Still Matter After Calibrating Answerability Readouts
Answerability readouts predict whether a passage supplies an answer, but whether calibration can compensate for removing negative passages during training remains unclear
- PaperResidual-Based Adaptive Refinement in Hybrid Variational-Collocation PINNs for Singular Elliptic PDEs with Mixed Dirichlet-Neumann Boundary Conditions
Solutions of second-order elliptic PDE problems on nonconvex or cracked domains with mixed Dirichlet-Neumann conditions typically lie outside $H^2(Ω)$. Near re-entrant co
- PaperProgressive multi-scale tumor-state memory for incomplete multimodal brain tumor segmentation
Brain tumor segmentation uses complementary magnetic resonance imaging (MRI) sequences, but some sequences may be unavailable in practice. Their absence changes the infor
- PaperRegime-Aware Interpretable Ranking for Sector Rotation
Sector rotation is a common decision in benchmark-relative portfolio management, where portfolio managers rank sectors for overweight and underweight positions. We formul
- PaperALIGN: Aligning Condition Estimation and Expression in Advantage-Conditioned Behavior Cloning
Human-collected robot manipulation data often mix successful behavior with retries, pauses, recoveries, and failures. Advantage-Conditioned Behavior Cloning (AC-BC) can e
- PaperLearning What to Remember: Resource-Efficient Self-Improvement for Lifelong Agents
Self-improving agents aim to continuously improve their behavior by learning from experience after deployment. However, accumulating and reusing more experience does not
- PaperWhen Guidance Becomes a Guard: Early Interception of Unsafe Inputs in Text-to-Image Generation
Text-to-image diffusion models can produce unsafe content, while output filtering intervenes only after synthesis. We investigate whether native generation signals enable
- PaperTeleASR-Amharic: A Benchmark for Robust Amharic ASR in Realistic Telecommunication Conditions
The real-world usability of ASR models remains challenging, particularly for low-resource languages, where existing speech resources are often collected in clean studio e
- PaperLabel Authority in Speech Emotion Recognition: Intended and Perceived Ground Truth in Emozionalmente
Ground truth in Speech Emotion Recognition (SER) is often presented as a single categorical fact, yet an acted emotion and the emotion heard by listeners describe differe
- PaperWenSight-Decision-1 for Direct Decisions under E-commerce Rules
E-commerce decisions require applying natural-language rules to the available case evidence. We introduce WenSight-Decision-1, a shared model that scores supplied options
- PaperRethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation
Fine-tuning large language models (LLMs) on downstream tasks often weakens their previously aligned safety behavior, creating an inherent trade-off between task adaptatio
- PaperReliable Estimation of Differential Privacy under Selection Bias
Statistical privacy audits are essential for verifying the theoretical privacy guarantees of differentially private (DP) mechanisms. Auditors typically use Membership Inf
- PaperFake News, Real Crashes: Information Injection Attacks on LLM Financial Trading Agents
Large language model (LLM) agents now trade real capital using news as evidence, yet they cannot reliably tell fabricated headlines from real news. Because they read 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.