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…
Saturday 17 October
- PaperSelm: Self-Evolving Library Management for Multi-Skill Agent Optimization
Large language model (LLM) agents increasingly use skills as a lightweight way to acquire task-specific knowledge. Recent work enables skills to evolve from task trajecto
- PaperMuse Glimmer 30B: An On-Device Agentic Model
We introduce Muse Glimmer, an open-source 30B parameter causal language model with perception encoder, purpose-built for autonomous agentic tasks on consumer hardware. Mu
- PaperUncovering Semantic Hierarchies in Text-Attributed Graphs via Variational EM-based LLM-GNN Synergy
While hierarchical structures are intrinsic to organizing human knowledge, current representation learning on text-attributed graphs predominantly operates on flat semant
- PaperBeyond Geometric Closure: Measuring and Diagnosing Mechanical Consistency in Visual Dynamics
Visual accuracy, geometric validity, and agreement with applied forces are distinct requirements for visual dynamics. We introduce a diagnostic framework that connects re
- PaperSafety Kernel: Mechanistic Alignment for Cross-Lingual Defense in LLMs
The safety capabilities of large language models (LLMs) are highly uneven across different languages, often allowing cross-lingual attacks to bypass safety guardrails. Ex
- PaperHow Much Do Activation Monitors Benefit from Original Model Computations?
One powerful way to safeguard AI systems is to monitor their internal computations--where signs of undesirable behavior might be more easily detectable than from models'
- PaperHSPR: Recovering Software-Agent Benchmark Scores via Hierarchical Posterior Inference
Evaluating software agents on a full benchmark is expensive. A small task subset can preserve agent rankings while yielding inaccurate scores. Historical responses provid
- PaperIntriAdapt: Generalizable Intrinsic-Guided Test-Time Adaptation for Metric Geometry Estimation
Recovering metric 3D geometry from images is fundamentally ill-posed due to perspective projection ambiguity. Current geometry models incorporate supplied or predicted in
- PaperSCOPE-VSR: A Broad-Coverage Training Dataset for Video Super-Resolution
Open-domain video super-resolution (VSR) requires temporally coherent details across widely varying scenes and subjects. However, existing training datasets are often sem
- PaperDynamic self-ensemble on multi-exit residual vision transformer for small-data image classification
Vision Transformer (ViT) has garnered increased attention for image classification in recent years. However, ViT is notorious for its data-hungry problem as it achieves h
- PaperTCMScience: An Autonomous Scientist for Traditional Chinese Medicine
Traditional Chinese medicine (TCM) research connects classical texts, medicinal entities, molecular assays, computational predictions, and clinical studies. An autonomous
- PaperSeverity-Channel Conditioning: An Injection-Level Study for Consumer-Device Deblurring
Motion-deblurring models lose substantial accuracy when transferred from professional cameras to smartphone-derived imagery. This paper studies whether a severity descrip
- PaperAdamPM: Memory-Efficient LLM Optimization via Moment Pooling
Adam is widely used for training large language models (LLMs) owing to its strong optimization performance and training stability, but its element-wise estimation for the
- PaperCADS: Measuring the Incremental Contribution of LLM Proposers in Sequential Biological Screens
Large language models are increasingly used to guide sequential biological screens, yet standard evaluations rely on raw hit counts that conflate a proposer's value with
- PaperTraining with Ciphers to Enhance In-Context Terminology Learning For Translation from Rare Languages
Fine-tuning LLMs with in-context examples (IC-Train) lets translation models adapt to new parallel data at deployment, but it is unclear whether they actually learn the t
- PaperScene-Adaptive VLA: Efficient Autonomous Driving via Dynamic Layer Routing
Vision-Language-Action (VLA) models offer a promising paradigm for autonomous driving. However, the massive parameter scale of VLAs strains onboard computational resource
- PaperConditional Weight of Evidence for Gradient-Boosted Credit Models: Estimation, Additivity and Its Relation to Adverse Action Reasons
Traditional weight of evidence assigns a credit characteristic a value based on its association with default across a population. Credit analysis also requires an assessm
- PaperDeliMF: Gated Cross-Attention Fusion of Structured Time Series and Clinical Text for Early Intensive Care Delirium Prediction
Delirium affects a large fraction of intensive care unit (ICU) patients and foreshadows longer stays, lasting cognitive decline, and higher mortality. Flagging the patien
- PaperConcordance Plausibility Check for Intervention-Conditioned Human Digital Twins
Intervention-conditioned human digital twins predict treatment alternatives that cannot be observed in the same patient. Ordinary predictive accuracy therefore cannot est
- PaperASR Personalization in Pathological Voice: Accuracy, Efficiency, and Duration Effects
Automatic Speech recognition (ASR) struggles with Pathological speech due to persistent speaker-specific mismatch. In clinical and accessibility scenarios, only limited t
- PaperRepresentations Have Trajectories: Characterizing Temporal Representation Dynamics in Neural Networks
Recent work has shown that deep neural networks exhibit an implicit low-rank simplicity bias. In this paper, we investigate the questions that naturally arise from this o
- PaperNo-Regret Revenue Maximization in Sequential Market Making Under Inventory Constraints
Market makers keep trading efficient by setting bid and ask prices for buyers and sellers. In sequential market making, trades happen independently based on price thresho
- PaperControllable Multi-Object Insertion for Detection Data Augmentation
Controllable object insertion provides a targeted approach to augmenting object detection datasets that require category--count fidelity, annotation alignment, and source
- PaperFrom Stories to Features: Scaling Concept Vectors for AI Alignment & Interpretability
We study feature vectors: directions in a language model's activation space that correspond to human-interpretable concepts, such as honesty or deception. Existing unsupe
- PaperCodec-Compatible Learned Compression for 3D Gaussian Splatting
Video-based 3D Gaussian Splatting (3DGS) compression methods provide a practical route by representing Gaussian attributes as 2D maps and coding them with standard video
- PaperCARVS: A Congestion-Aware Algorithm for Online Multi-Agent Pickup-and-Delivery in Human-Collaborative Warehouses
Intelligent warehouse systems have transformed logistics by integrating robots with minimal infrastructure changes, boosting efficiency and optimizing workflows compared
- PaperCross-polarization pairing for label-free few-shot thin-section classification
Few-shot classifiers of rock thin sections are meta-trained on many rock types that a petrographer has identified slide by slide, and this identification is the costly st
- PaperWhen Code Becomes an LLM Call: An Empirical Study of Call-Site Contracts in Agentic Systems
Software quality has long rested on specifications that state what code must do, and on testing and verification that check that the code does it. Agentic systems change
- PaperTheory-Guided Instance-Dependent Early Stopping via Second-Order Loss Dynamics
Instance-dependent early stopping (IES) reduces training computation by skipping backpropagation for examples whose losses have stabilized, but the second-order loss-diff
- PaperEGIP: An Evidence-Grounded Interaction Protocol for Clinical Agents
Interactive clinical agents acquire evidence through patient dialogue and diagnostic examinations, yet their performance also depends on how the interaction environment e
- PaperAccelerating Finite-Sum Bilevel Optimization with Fully First-Order Oracles
We study nonconvex--strongly-convex bilevel optimization with finite-sum objectives and fully first-order oracles. We propose Sampled Implicit Corrections for Bilevel Opt
- PaperWrite Once, Query Many: Evolving Compact Reusable Memory for Long Videos
Long videos often exceed the context capacity of multimodal large language models (MLLMs), while agentic search repeats costly video processing and grounding for each que
- PaperA Multi-Step Inertial ADMM Algorithm for Federated Learning
Federated learning has recently emerged as an important paradigm for large-scale distributed model training, which can be naturally formulated as a class of distributed l
- PaperFrom Score to Diagnosis: Search-Independent Post-Diagnosis for Symbolic Regression
Symbolic regression (SR) solvers employ diverse search mechanisms, yet most rely on the same low-information scalar fitness. Such scores provide little guidance on why a
- PaperStructured Latent Dynamics for Long-Horizon Embodied World Models
Reliable long-horizon prediction remains a central challenge for embodied world models. Although recent generative models can synthesize visually plausible action-conditi
- PaperGTSM: Gaussian Splatting with Thermal State-Space Dynamics for Spatio-Temporal Thermal Field Reconstruction and Prediction
Temperature-field reconstruction and prediction are important for condition monitoring, process analysis, and state assessment in industrial and dynamic environments. Thi
- PaperContrastive Hypergraph Source-free Domain Adaptive Object Detection in Adverse Weather Conditions--Extended Version
Adverse weather conditions such as fog, rain, snow, and low illumination introduce structured visibility degradations that severely impair object detectors trained on cle
- PaperAn Optical Music Recognition Tool for String Quartets
This paper presents an optical music recognition (OMR) system tailored for PDF scores of string quartet pieces. The approach begins with a SegNet-based segmentation model
- PaperRethinking EEG Spatial Super-Resolution as Dynamic State Decomposition and Filtering
EEG spatial super-resolution aims to recover high-density neural signals from sparse electrode observations. Existing methods have achieved substantial progress through s
- PaperVisConf: Quality-Aware Consensus for Best-of-N in Vision-Language Model Reasoning
Best-of-N methods improve text-only LLM reasoning by sampling multiple trajectories before selecting an answer. For Vision-Language Models (VLMs), answer frequency and mo
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.