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…
Thursday 15 October
- PaperMeasuring the local shape of learning-rate transfer curves
Understanding the learning-rate (LR) dependence of trained model performance is essential for better optimization of neural networks, but the appropriate size of the LR d
- PaperN-Gram Memories at Two Bits: Quantizing Lookup Tables in Large Language Models
Conditional memory expands language-model capacity through selective lookup, but the full embedding table must remain available for every possible input. We introduce Con
- PaperFrom Adults to Children: Benchmarking Foundation Models for Chest X-Ray Classification under Domain Shift
Foundation models have shown significant potential across diverse fields and have been applied to medical imaging, but their robustness across patient populations remains
- PaperRoleQ: Role-Aligned Scales for Converting Language Models to Ternary
Weight quantization below four bits shrinks memory and bandwidth at a perplexity that looks acceptable, but often at the cost of factual knowledge and task accuracy. Tern
- PaperContent associations with answer selection and engagement in supply chain community question answering
Community question-answering platforms are important ecosystems for knowledge sharing, yet research on what makes an answer best or a question engaging has often focused
- PaperCIM-Embed: Learning Instruction-Conditioned Multimodal Embeddings for Clustering
Multimodal objects can require different partitions under different instructions, as when products in an e-commerce catalog are grouped by color, material, or both. Retri
- PaperCo2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration
Incremental learning (IL) aims to continually acquire new knowledge (plasticity) while retaining previously learned information (stability). However, striking a balance b
- PaperTeaching DINOv3 About Partial 3D Geometry: A Self-Supervised Geometry-Aware Approach
Partial shape matching is a crucial yet underexplored problem in 3D vision, with significant relevance to real-world scenarios where shapes are often only partially obser
- PaperBehavioral Forgetting Is Not Privacy in Machine Unlearning
Machine unlearning aims to remove targeted information from large language models, but existing evaluations often measure forgetting only on a designated benchmark distri
- PaperCross-Embodiment Causal Transfer from Human Videos to Robot Manipulation
Scaling robot manipulation models requires large amounts of interaction data, yet collecting diverse real-robot experience remains costly. Human manipulation videos, in c
- PaperSingle-stage joint diffusion of sky images and clear-sky index for ultra-short-term irradiance forecasting: what the frame-to-irradiance stage discards
Sky-image irradiance forecasting is dominated by a two-stage design: a video-prediction model forecasts future sky frames, and a separately trained regressor maps those f
- PaperMedPAO-VL: Interpretable and Protocol-Compliant Agent for Structured Radiology Report Generation
Despite the remarkable generalization capabilities of Large Language Models, generating clinically accurate and structured radiology reports from medical images remains a
- PaperRSIFlow: Adaptive Self-Improvement Workflows with an Evolving Meta-Agent
Large language model (LLM) agents have demonstrated strong capabilities in complex tasks, including code generation, tool use, and multi-hop question answering. Existing
- PaperIn the Guise of Correction: How Framing and Cultural Adaptation Erode LLM Safety on Real-World Criminal Cases
Existing safety benchmarks rely largely on synthetic prompts with loosely grounded taxonomies and offer little focused analysis of severe crime categories. We introduce G
- PaperNICE Toolbox: Nonverbal Interpersonal Communication Exploration Toolbox
Understanding human communication is a long-standing goal in psychological research. People express themselves through many verbal and nonverbal channels: posture, gestur
- PaperLearning to Think and Explore in 3D World
We study how vision-language models (VLMs) can learn to think and actively explore in 3D space. Instead of providing multi-view images, videos, or 3D representations to t
- PaperDINO-FIL: Multi-Layer Transformer Fusion for Generative Inpainting Forgery Localization
We propose DINO-FIL, a transformer-based framework for pixel-level localization of generative image forgeries. The method leverages multi-layer representations from a pre
- PaperFuseAdapt: Parameter-Efficient Multimodal Fusion for Semantic Segmentation with Missing Modalities
Multi-modal semantic segmentation benefits from complementary sensors, but this benefit is fragile when some modalities are degraded or missing at test time. Many existin
- PaperSame Spectrum, Harder First-Order Training: Phase-Locking in Single- versus Multi-Qubit Re-Uploading Circuits
Angle-encoded variational quantum circuits implement truncated Fourier series. For one-dimensional inputs, a single-qubit re-uploading (serial) circuit represents every f
- PaperCF-AVSS: A Coarse-to-Fine Audio-Visual Speech Separation Framework with Target-Speaker Refinement and Post-Fusion for Real-World AVSE Challenge
Audio-visual speech enhancement (AVSE) leverages visual cues to recover target speech from mixtures corrupted by reverberation, noise, and overlapping speakers. We propos
- PaperFrom Research Goals to Scientific Closure: Evaluating Agents Through Evidence-Supported Physics Research
Can AI agents organize scientific investigations that lead to well-supported conclusions? To evaluate this capability, we introduce PhysClosureBench, a benchmark of 50 ex
- PaperQ($γ_H$): Entropy-Guided Horizon Mixing in Multi-Discount Q-Learning
A fixed discount factor in Q-learning imposes a single planning horizon throughout training, despite the differing demands of early exploration and long-term credit assig
- PaperBias Mitigation in Audio-Enabled LLMs through Adversarial Training and Distillation Methods
Audio-enabled large language models (AuLLMs) allow users to interact with them simply by talking to them, without the need for an intermediate transcription. This expands
- PaperBeyond Generation: Using Multimodal LLMs as Detectors of LLM-Generated Deepfake Facial Images
As image generation models become increasingly capable of producing highly realistic content, traditional forensic techniques are struggling to keep up. This paper invest
- PaperBeyond Source Prompts: Towards Visually Grounded AI-Generated Video Quality Assessment
Recent advances in generative artificial intelligence have accelerated video generation technologies. However, AI-generated videos (AIGVs) remain susceptible to various d
- PaperDeciCAD: Harness-Grounded Learning of Action Policies for CAD Agents
Large Language Model agents operate through closed-loop action policies whose decision space is defined by an agent harness. We investigate how this operating space shape
- PaperHarmful Partial Interventions and Benign Leakage in Concept-based Models
Artificial intelligence systems deployed in high-risk settings increasingly require models that support meaningful human oversight. Concept-based models (CMs) offer a pro
- PaperThe Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks
Spiking neural networks (SNNs) offer a compelling pathway toward energy-efficient artificial intelligence, fundamentally anchored in presynaptic input-driven sparsity. Ho
- PaperThe Delegation Dilemma: Economies of Scale, Accountability, and Polycentric Governance
Many collective-action systems are neither fully decentralized nor fully centralized: agents voluntarily organize into institutions that share organizational costs and de
- PaperPairwise AUC Optimization Needs Corrective Power: A Unified View
Direct pairwise AUC-surrogate training is attractive because it trains toward the ranking metric used at test time, especially under class imbalance. This creates a direc
- PaperSparse Federated Echo State Networks for Time-Series Classification via Smooth-L1 Regularization
Echo State Networks (ESNs), as lightweight implementations of reservoir computing, provide efficient solutions for temporal data processing in resource-constrained enviro
- PaperReliable Knowledge Acquisition for Continual Learning Agents
As agents powered by foundation models move into open-ended environments, continual learning from experience becomes essential. For agents built on models with fixed para
- PaperSceneWeave: Audience-Guided Scene Exploration for Dramatic Adaptation
Adapting prose into a script requires transforming narration and inner experience into scenes that convey relationships and psychological contradictions. Planning specifi
- PaperIn-Context Preference-Conditioned Pareto Set Learning from Limited Offline Data
Multi-objective optimization involves diverse preferences over conflicting objectives. Rather than returning a finite set of trade-off solutions, preference-conditioned P
- PaperRetrieved but Not Read: Understanding Why Search-Augmented LLMs Fail to Use Available Evidence
Web search allows LLMs to access up-to-date information, but it remains unclear why they sometimes produce outdated answers even when relevant evidence is available. To s
- PaperFIRM: Fisher-Informed Retention Merging for Federated LLM Unlearning
Federated LLM unlearning addresses targeted knowledge removal when forget and retain data remain distributed across private clients and are inaccessible to the server. Th
- PaperInternational Multi-Centre Validation of Unsupervised Domain Adaptation for Precise Discrimination between Normal and Abnormal Retinal Development
Arrested retinal development can cause childhood visual impairment, but grading optical coherence tomography scans is difficult to standardise across devices and centres.
- PaperEncoded but Exposed: Language Embeddings can Reveal More Than They Should in Recommender Systems
Language embeddings are increasingly used in recommenders to represent item content, but their privacy risks remain poorly understood. We study whether item embeddings ca
- PaperRobust Covariance Estimation for Entry-wise Contaminated and Partially Observed Data via Expectation Maximization Algorithm
Robust covariance estimation under entry-wise contamination and missing data is challenging in various signal processing applications. Under the Student-$t$ model, observ
- PaperHuman Interventions as Labels: Localizing, Steering, and (Sometimes) Editing the Computations Behind LLM Agent Failures
When an LLM agent misbehaves, a human steps in, and that intervention is usually discarded or replayed as training data. We treat it instead as a measurement: a label poi
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.