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…
Yesterday
- PaperExploring Recurrent-Depth Language Models for Multitask Clinical Text Processing
Clinical natural language processing includes diverse tasks such as information extraction, classification, and question answering. Developing one model for all tasks cou
- PaperAnchorRM: Parallel Intra-Batch State Reconstruction with Anchor-Based Residual Memory for Temporal Graph Neural Networks
Memory-based temporal graph neural networks (TGN) rely on recurrent node memories to capture evolving interaction histories. However, temporal mini-batching introduces a
- PaperCan Native Safety Travel? Reusing Safety Pretraining Across Models via On-Policy Distillation
Safety pretraining has emerged as a promising paradigm for embedding safety deeply into a model during pretraining, yielding robustness to subsequent fine-tuning that con
- PaperLower Bounds for Smooth Nonconvex Zeroth-Order Optimization: The Price of Determinism under Low Curvature Trace
Low curvature trace, an effective rank condition, is a common explanation for why randomized zeroth-order methods scale to high-dimensional tasks such as language model f
- PaperTiming-Aware and Interpretable Self-Attention for Event-Based Wearable Task Transition Detection
Task transition detection aims to identify when a person shifts from one task to another, providing a foundation for continuous health monitoring and timely context-aware
- PaperAct on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization Alignment
When an LLM agent acts on behalf of a user, it is expected to act within the authorization scope the user grants. Existing agent evaluations largely measure task completi
- PaperSynCalib: Breaking Dataset Shortcuts in LiDAR-Camera Calibration via Extrinsic-Controllable Synthesis
Online LiDAR-camera calibration remains a fundamental yet challenging task in the field of robotics. Recently, deep learning-based data-driven approaches have emerged, of
- PaperBEACON: Bridging Multimodal Semantics and Asynchronous Propagation for Cloud System Anomaly Detection
Modern large-scale cloud systems continuously generate massive and multimodal observability data, such as time-series metrics, log records, and system dependency graphs,
- PaperEviDial: When Correct Depression Predictions Lack Evidence
Depression dialogue benchmarks commonly assess models by comparing predicted symptom labels with clinical scale scores. However, a prediction may agree with a benchmark l
- PaperLess is More: Concise Retrieval and Critic-based Re-ranking for Composed Image Retrieval
Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image based on a reference image and modification text. Recent approaches commonly rely on large vis
- PaperWhat Moved the Alarm Score? Causal Attribution with Exact Computation and Scarce-Incident Estimation
Alarms in industrial systems and scientific instruments often demand immediate diagnosis despite scarce incident data. To guide intervention, an explanation must trace ho
- PaperAdversarial Benchmarks and BenchDoor Attacks: Exploiting Benchmark Incentives for Backdoor Attacks
Machine learning benchmarks act as guideposts for model development and spur the creation of training datasets intended to improve benchmark scores. We introduce BenchDoo
- PaperAutomated Multi-Agent Organization Design: From Architecture Search to Organizational Learning
Agentic system design is increasingly shifting from hand-crafted prompts and workflows toward automated search over agentic programs and interaction structures, with mult
- PaperJudging the Justification: Decision Certificate Supervision for Generative Reward Models
Generative reward models (GenRMs) generate natural language rationales to justify preference judgments, yet a correct verdict does not guarantee a sound justification. Ex
- PaperMemDev-Bench: Does Memory Help Code Agents?Benchmarking Memory Systems over Real Repository Histories
Code agents increasingly work on evolving real repositories, and memory systems aim to help them reuse earlier experience. However, such experience is diverse and evolvin
- PaperOmniVLoc: Topo-metric Visual Localization for Omnidirectional Cameras
Omnidirectional cameras provide surround-view information, significantly overcoming the field-of-view constraints for traditional visual localization systems. However, ex
- PaperMultiscale Temporal-Spectral-Spatial EEG Learning With Modality-Specific and Modality-Invariant Representations for Emotion Recognition
Multimodal physiological signals provide complementary cues for emotion recognition. They also raise two related challenges. Emotion-related EEG patterns vary across time
- PaperWhen Health Assistants Agree Too Readily: A Benchmark of Time-Critical Self-Diagnosis
Every day, more than 40 million people ask ChatGPT a health question, such as whether laptop posture explains a stiff neck and days of pounding headache. Posture is plaus
- PaperHealBench: A Fine-Grained Benchmark for Evaluating Psychological Comfort in Text-to-Image Generation
Despite advances in photorealism, semantic fidelity, and aesthetics, text-to-image generation and image editing remain understudied in a human-centered dimension: whether
- PaperProgressive Subset Selection and Cascaded Consistency for Unsupervised Vision-Language Model Adaptation
Pretrained Vision-Language Models (PVLMs) achieve strong zero-shot recognition but often suffer performance degradation under target-domain shift. Unsupervised adaptation
- PaperStructured-Token Attention for Fine-Grained mmWave Liquid Identification
Fine-grained liquid identification requires a classifier to distinguish similar substances from compact millimeter-wave measurements. We investigate structured-token atte
- PaperCross-Visibility-Gap Identity Persistence for 4D Scene Graphs
4D scene graphs require persistent object identity when an object disappears inside an opaque carrier and later reappears as a fresh detection. When appearance and target
- PaperSoliton Profiles in 1D: Enhanced Neural-Network Solvers and Constrained Deep Ritz Methods
We develop and compare enhanced neural-network solvers for one-dimensional ground-state profiles, which are solutions of $$ Q^{\prime\prime}=bQ-γQ^{p},\quad Q>0,\quad p>1
- PaperSelf-Evolving Agents through Privileged Retrospective Distillation
Self-evolving agents aim to improve from their own experience rather than remain fixed after deployment, but naturally collected trajectories often lack ground-truth solu
- PaperMiCLA: Mixture-to-Constituent Latent Alignment for Polyphonic Audio Representation Learning
Real-world audio typically contains concurrent sound events, yet standard self-supervised methods treat each clip as an isolated training unit without explicitly modeling
- PaperOrthogonal Boundary Unlearning for Dual-Use Concepts in Large Language Models
Mitigating catastrophic risks from large language models requires excising hazardous operational capabilities, such as cyberwarfare exploitation and pathogen enhancement,
- PaperThe More the Better? A Comparison of Single- and Multi-Agent LLM Setups on a Financial Review Task
Practitioner guidance holds that a large language model reviews a document better when the work is divided among agents. We test a narrow form of it in a controlled compa
- PaperSecuring Agentic Commerce Through Behavior-Aware Fraud Detection and Cybersecurity for Trusted AI-Agent Payment Authorization
The growing use of autonomous artificial intelligence agents in digital commerce creates new security concerns involving agent impersonation, unauthorized payments, compr
- PaperRuntime Control for AI Agents: Closing the Evaluation--Execution Gap in Operational Workflows
Language-model agents increasingly participate in operational workflows where approvals, binds, and payments create commitments. An approval valid when issued may no long
- PaperFocusOVD: Geometric and Contextual Feature Refinement for Open-Vocabulary Small-Object Detection
Open-vocabulary object detection aims to detect both seen and unseen categories by leveraging the semantic knowledge of vision-language models. However, existing methods
- PaperWhen Parameter Gradient Flows Close in Representation Space
The represented gradient flow of a parameterized model depends on a mobility that can retain hidden parameter information. We study when one entire represented mobility m
- PaperBeyond the Prompt: Recovering Hidden Concepts in Text-to-Image Models
Text-to-image models can generate visual concepts that their prompts never mention, and recent work shows that such associations can be implanted so that ordinary prompts
- PaperPrivacy-Preserving Personalized Federated Learning (PPP-FL) for Medical Imaging
Federated learning (FL) is a distributed machine learning paradigm that reduces transmission costs, mitigates cross-border data sharing restrictions, and enhances privacy
- PaperTraining-Free Continual Learning for Multimodal Forecasting via Prompt Evolution
Adapting a forecasting system to a changing world classically means retraining. We ask whether the task of continually learning regimes for time series forecasting can be
- PaperProjected Distillation: On Learning to Solve Hard Problems from Close, Correct Targets
On-policy learning is central to post-training: training on a model's own generations limits distribution shift and helps preserve existing capabilities. On hard problems
- PaperRecoverability and Verifier Strength: Two Measured Preconditions for Unattended Agent Self-Improvement
Agent platforms are starting to improve their own agents: they read a deployed agent's execution traces, derive a change, have an automated verifier approve it, and relea
- PaperDetecting Errors in Large Language Model Responses: The Incremental Predictive Value of Hidden States
Although large language models support a wide range of tasks, hallucinations remain a major obstacle to user trust. When a model generates an answer, both its internal pr
- PaperAsk to Distill: Learning to Synthesize Data for On-Policy Distillation
On-policy distillation (OPD) can succeed with surprisingly few training questions, motivating a view of questions as carriers of distributional knowledge transfer. How ca
- PaperBeyond Scalar Leaderboards: Adaptive Sampling for Pareto Frontier Identification in Multi-Objective LLM Arenas
The evaluation of large language models (LLMs) is inherently multi-objective, as different models may offer different tradeoffs across performance dimensions such as math
- PaperDecision Sufficiency of Learned Representation Interfaces for Safe Generative Control
A controller can guide a language model toward safe and useful responses by choosing when to assist, ask for clarification, or refuse. When the controller uses selected i
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.