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…
Tuesday 20 October
- PaperA Process-Informed, Photorealistic Digital Twin for Vision-Based Inline Inspection of C-SMC Strip Deposition
Inline quality assurance for Sheet Molding Compound (SMC) manufacturing is hindered by the lack of large-scale, accurately labeled image datasets for training machine-lea
- PaperOn-Policy Transition Distillation
On-policy distillation (OPD) consolidates expert capabilities into a single student by matching teacher and student final-layer distributions on student-generated rollout
- PaperPoisoning-Based Backdoors Are Not Cryptographic
To defend against backdoor attacks on neural networks, the defender must identify the verifier function that determines whether an input is a trigger, rather than rejecti
- PaperUsing Letter Positional Probabilities to Assess French Word Complexity
We use Letter Positional Probabilities (LPPs) to examine the orthographic differences between simple and complex French words. We draw from a sample of 38,000 French word
- PaperWhen Does Training on Synthetic Data Provably Work?
High-quality training data are a major bottleneck in machine learning, motivating increasing use of artificially generated data. We study when a binary classifier trained
- PaperSpherical Geometry-Aware Panoptic Scene Graph Generation for Equirectangular Panoramas
Panoptic scene graph generation (PSGG) represents scene entities with segmentation masks and directed relations. Equirectangular projection (ERP) panoramas challenge PSGG
- PaperFrom RL Papers to Framework Code: Inclusion and Review in Seven Open-Source Training Frameworks
Practitioners use reinforcement learning methods for language models through training frameworks, so a method that a framework includes is one configuration change away f
- PaperP$^3$-VLM: A Point-based Alternative for Grounded 3D Vision-Language Models
Examining existing benchmarks for grounding in 3D VLMs reveals a pervasive "semantic leakage" in the evaluation and prompting protocols: a heavy reliance on bounding boxe
- PaperRANGER: Retrieval Agent for Navigating Graphs with Semantic Evaluation Rewards
The integration of Large Language Models and Reinforcement Learning offers a promising direction for complex sequential decision-making tasks, such as multi-hop question
- PaperAdaptMIL: Domain Adaptation for Multiple Instance Learning in Digital Pathology
Pathology foundation models (PFMs) support a wide range of histopathology tasks on whole-slide images through multiple instance learning (MIL). Despite recent progress, t
- PaperDifferentiable Task-Driven Coded Aperture Camera Design with 3D Gaussian Scene Representations
Camera design heavily influences perception task performance, yet cameras are typically designed by domain experts through costly experimentation, in isolation from the t
- PaperDancing Diffusion: Learning Continuous Programs for Image Generation and Editing
Diffusion models generate samples through a multi-step denoising trajectory, yet condition every step on the same instruction, so the trajectory cannot be addressed at th
- PaperBeyond the Evidence Boundary: Behavioral Mirage Under Progressive Degradation in Medical VLMs
VLMs for medical image interpretation are typically evaluated on clean inputs, despite the progressive evidence loss that can occur in high stakes clinical settings. Exis
- PaperMatrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds
Moving from controllable videos to genuinely playable worlds requires persistent world state, executable game rules, and low-latency interaction. We outline a roadmap for
- PaperLearning Tactile-Aware Hand Representations from Human Hand-Object Interaction Data
Tactile representation learning for dexterous manipulation often requires substantial robot-side data collection, limiting its scalability across different hands and sens
- PaperBuilding Telecom Language Models with RSOD: Domain Data, Specialist Post-Training, Memory-Conscious Distillation, and Networking Evaluation
Telecom language models must combine broad networking knowledge with specialist behavior across routing, broadband services, access technologies, and operational diagnost
- PaperWhen Momentum Helps Polyak--Ruppert Averaging
Polyak--Ruppert averaging gives SGD and momentum methods the same asymptotic covariance. We characterize how fast finite runs reach it and how far they can be parallelize
- PaperOn Johnson-Lindenstrauss Transforms for Byzantine-Robust Optimization
The growing scale of data and models in machine learning calls for efficient optimization methods. Distributed optimization addresses this challenge, with compression mec
- PaperRecast the Past: Stable Long Video Generation with Full Context Memory
Long-horizon video generation requires retaining an ever-expanding history, but conditioning on its growing token sequence is costly. Existing methods restrict or compres
- PaperAnnealed correlation and quenched noise sensitivity in biased deep neural networks
In earlier work by Jonasson, Steif and Zetterqvist (2023), fully connected deep neural networks with layers of width $n$, i.i.d.\ standard Gaussian weights, sign activati
- PaperBeyond the Frame: Redundancy, Not Trajectory, Carries the Privacy Leak in Video Unlearning
Class unlearning for video segmentation aims to ensure that a removed category cannot be reconstructed from a deployed model's outputs. Current leakage evaluation algorit
- PaperAdaptive Stopping of Streamed Reasoning for Language Model Agents
Reasoning-enabled language model agents can incur substantial computation before acting, although the reasoning needed varies across decisions. Existing stopping signals,
- PaperMedia Intelligence Platform: Multimodal Detection of Synthetic and Manipulated Content
The rapid progress of generative artificial intelligence has led to a significant increase in manipulated multimedia content, including synthetic faces, forged videos, AI
- PaperNeural Closed-Loop Identification of Nonlinear Systems with Stability and Generalization Guarantees
Neural networks are expressive models of nonlinear dynamics, but identifying such systems from closed-loop data raises two difficulties: the feedback loop correlates inpu
- PaperWhen Do Humans and Machines Truly Complement Each Other? Formal Conditions and Empirical Evidence for Human-AI Synergy
Can humans and artificial intelligence cooperate such that their combination yields greater accuracy than either agent alone? This result, termed \emph{synergy} or \emph{
- PaperEfficient SAM3 Adaptation for Multi-Class Semantic Segmentation via Dense Competitive Representations
The Segment Anything Model 3 (SAM3) has achieved significant progress in Promptable Concept Segmentation (PCS) by processing short noun phrases to generate segmentation m
- PaperFrom Proper Scoring Rules and Edge Biases to Mumford-Shah Models: Robust Unsupervised Hyperspectral Image Segmentation
Hyperspectral images provide a rich representation of the underlying spectrum for each pixel, allowing for a pixel-wise classification/segmentation into different classes
- PaperLost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay
Recent advances in large (vision) language models have enabled computer-use agents that automate digital workflows via fine-grained keyboard and mouse operations. However
- PaperUnsupervised Head Network Personalization for Split Computing via Federated Learning
Split Computing (SC) is a distributed inference method designed for balancing computational load and reducing latency by partitioning a neural network into head and tail
- PaperEdit in Sync: Unified End-to-End Audio-Visual Editing for Human-Centric Videos
Human-centric audio-visual editing requires precise alignment of lip movements, gestures, and expressions with speech. Existing methods process inputs through independent
- PaperDecoupling Action from Egocentric Observation for World Simulation
Egocentric action transfer aims to decouple the semantic action from egocentric observations and reproduce them in new visual contexts, enabling scalable world simulation
- PaperIn PRAISE of Attributes: Grounding Retrieval Geometry with Query-Conditioned Subspaces for Person Re-Identification
Person re-identification (ReID) ranks an image gallery using either an image query or a textual query. In image-to-image (I2I) ReID, viewpoint, illumination, occlusion, a
- PaperNear-Duplicate Image Selection Transfers Preferences in Vision-Language Models
Subliminal learning is the phenomenon in which a model transmits its preferences to another model through data that do not explicitly express them. As models increasingly
- PaperAPRIL: Ambiguity-Aware Expert Routing for Respiratory Sound Domain-Incremental Learning
Automated respiratory sound classification enables continuous, non-invasive respiratory assessment, yet long-term deployment remains challenging due to domain shifts from
- PaperHypTI: Hyperbolic Geometry-Aware Multimodal Feature Fusion Framework for Dementia Detection Based on Tabular-Image Data
AI-assisted dementia detection usually requires multimodal fusion of diverse data, such as clinical tabular assessments and neuroimaging data. However, most existing appr
- PaperFrom DQI to C-DQI: Automatic Codebook Generation and Evaluation for Measuring Computational Discourse Quality Index
Effective democratic deliberation is vital for civic engagement and the health of legislative institutions. However, assessing parliamentary discourse quality is traditio
- PaperFrom Comparison to Selection: Enhancing Cross-Scale Generalization of Pointer Networks Trained with Reinforcement Learning for Capacitated Drone Delivery Routing
Unmanned aerial vehicles (UAVs) enable fast, flexible last-mile and emergency delivery, but their routing remains challenging as the number of clients varies. Classical a
- PaperWhy Do LLMs Accept Generics? Explaining Acceptability using Psycholinguistic and Model-Derived Factors
Psycholinguistic studies explore why humans accept some generic statements but reject others by showing that these judgments depend on more than how common a property is.
- PaperQuantum-JEPA: Quantum Born Priors for Latent-Action JEPA World Models
A single observation can admit several plausible futures, making uncertainty an essential part of world modelling. However, quantum generative models remain underexplored
- PaperWorld Models with Configurable Perception
Real-world observations are noisy and often contain excessive task-irrelevant information. Effective world modeling and planning need to abstract observations into world
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.