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
- PaperMELD: Recursive Self-Improvement via Hierarchical Coordination for Multi-Agent Scientific Discovery
Multi-agent scientific discovery with large language models raises a coupled learning problem: research assignments determine both which experiments are pursued and the e
- PaperHippo: Training-Free Agent Self-Evolution via Hippocampal Replay
Motivated by recursive self-improvement (RSI), we study how LLM agents can learn through external memory without updating model parameters. Extracting useful experience f
- PaperHumanSkill-4D: Training-Free Language Querying of Animatable Gaussian Avatars in Space and Time
We introduce avatar referring segmentation, which selects regions of animatable Gaussian avatars from language queries. A query can also specify a pose or motion to selec
- PaperDo 3D Large Language Models Really Use 3D Evidence?
Recent 3D Large Language Models (3D-LLMs) have shown strong performance on scene question answering with extensive post-training. Yet, existing benchmarks rarely evaluate
- PaperNear-Optimal Regret for Semi-Bandit Learning of Monotone Stochastic Problems
We consider the task of learning an (approximately) optimal policy for stochastic optimization problems where the true distributions are unknown. In each period, the algo
- PaperMemory Internalization via Test-Time Training for Long-Video Understanding
Long-video understanding often requires answering many questions about a single video whose evidence is distributed across extended temporal contexts. Conventional video-
- PaperUncertainty Gates the Gradient: Adaptive Updates for Generalized Few-Shot 3D Segmentation
In generalized few-shot 3D point cloud segmentation, support annotations are often compromised by sparsity and occlusion. Blindly adapting to such low quality samples ris
- PaperTransformers as Adaptive Kernel Learners across Tasks for In-Context Learning
Transformers have emerged as a dominant architecture in modern machine learning, with in-context learning (ICL) enabling models to adapt to new tasks by conditioning on p
- PaperBodyBridge: Grounded Body Layers for Sim-to-Real Translation of Vulnerable Road Users
Simulation-to-real driving video diffusion models can translate photorealistic scenes, but they typically represent pedestrians and cyclists, vulnerable road users (VRUs)
- PaperTransport What Shares the Conduction Pathway: Normal-Anchored SPD Geometric Transport for Source-Free Patient Adaptation of Holter and Patch ECG
Electrocardiogram (ECG) beat classifiers lose accuracy on new patients and devices, and source-free adaptation methods that assume class-balanced target batches fail on r
- PaperWhen Opposite Premises Translate Identically: A Source-Conditioned Diagnostic for Multilingual Commonsense Items
Multilingual reasoning comparisons depend on translated premises preserving the relations in their English sources. Automatic translation scores can rank source-target pa
- PaperMargin-Based Generalization for Quantum Machine Learning with Classical Data Encoding
Understanding generalization is essential for assessing the practical viability of quantum machine learning. In many applications, quantum models operate on classical dat
- PaperToward a Universal Local Speech Feature Extractor Through Distillation
Self-supervised speech models commonly consist of a set of convolutional neural network (CNN) layers used as a local feature extractor, followed by transformer layers. Th
- PaperCross-Dimension and Cross-Modality Relational Tensor Representation Learning for Multimodal Health Data Modeling
Multimodal health data integrate information from heterogeneous clinical sources, creating substantial opportunities for data-driven decision support. Realizing these opp
- PaperS3D-Mosaic: Subgradient-Guided Cross-Band Structure Transfer for Spectral Demosaicing
Multispectral filter array (MSFA) imaging enables snapshot spectral acquisition, but its per-band sparse sampling causes severe spatial aliasing. Although missing spatial
- PaperAsk Less, Ask Better: Allocating User Attention in Proactive LLM Agents with Interruption Budgets
LLM agents can ask clarifying questions to complete tasks, but answering each question demands users' time and effort. Existing evaluations typically measure this burden
- PaperLong Listening Thoughts: Eliciting Open Auditory Reasoning with Deliberative Perception and Cognitive Refinement
We introduce Long Listening Thoughts (LLT), a framework for constructing post-training datasets that improves audio reasoning by pairing deliberate perceptual grounding w
- PaperZeroDSS: Semantic Segmentation from Class Names Alone
Semantic segmentation depends heavily on real images with pixel-level annotations, making dense supervision a major obstacle to deployment in new domains. We study task-s
- PaperPrototype-Guided Optimization of Quantum Data Embeddings with Linear Cost
In supervised quantum machine learning with classical data, classification performance critically depends on the geometry induced by quantum data embedding. Existing data
- PaperSpatons: Spatiotonally Localized Building Blocks for Efficient XR Predistortion
We present Spatons, a family of compositional, spatially localized neural operators for computationally efficient XR (extended reality) predistortion and distortion compe
- PaperMSCR: Jointly Balancing Utilization Across Modalities and Discovering Synergistic Information
In multimodal learning, modality imbalance often lets one modality dominate optimization and keeps the model from fully exploiting cross-modal interactions. Balance-orien
- PaperTrust the Edge, Doubt the Arrow: Auditing Validation Signals for Text-Mined Clinical Causal Knowledge Graphs
Clinical causal retrieval-augmented generation systems increasingly use knowledge graphs (KGs) mined from notes, yet extracted assertions remain candidates that require a
- PaperLearning volatility-adaptive forgetting via GARCH-modulated LSTM for stock price forecasting
Stock price forecasting is hindered by the heteroscedastic nature of financial time series, in which turbulent and tranquil regimes alternate. Although the Long Short-Ter
- PaperBridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization
Effective test-time personalization requires LLM agents to adapt to query-dependent user preferences from lightweight interaction. We study persona selection with binary
- PaperA decomposition-integration framework coupling singular spectrum analysis with a volatility-adaptive LSTM for stock price forecasting
Financial time series exhibit multi-scale, high-noise, and non-stationary volatility dynamics. Decomposition--integration frameworks built on complete ensemble empirical
- PaperIF-MAP: Influence-Function-Inspired Agent Prioritization in Multi-Agent Systems
Improving every agent in an LLM-based multi-agent system can be prohibitively costly, making it important to identify which agent should be prioritized to achieve the gre
- PaperIs This Your Agent? Identity Watermarking for Agent Systems in Dynamic Environments
Agent systems deployed in dynamic environments continuously update their memories, skills, and runtime configurations, leading to evolving trajectories and challenges for
- PaperLearning from the Right Regions: Class-Conditioned Explanation Guidance for Medical Imaging
Deep neural networks can achieve strong predictive performance in medical imaging while relying on regions unrelated to the predicted finding. Explanation-guided learning
- PaperTrain Locally, Learn Together: Distributed Multi-Agent Training via ADMM
Multi-agent systems (MAS) can outperform individual language-model agents by combining specialized roles, diverse reasoning processes, and collaborative decision-making.
- PaperDefending Against Dormant Poisoning Attacks Across Language and Multimodal Agents
Recent work shows that attackers can implant dormant malicious behaviors that remain hidden at release but emerge after benign fine-tuning. As foundation models are used
- PaperPACE-Mem: Prefix-Aware Complementary Evidence for Multimodal Agents
As multimodal agents accumulate experience, their long-term memories contain many similar observations of recurring scenes, actions, and entities. Answer quality depends
- PaperBeyond Next-Screen Prediction: The Decision Value of GUI World Models
GUI world models are increasingly used to improve action selection by predicting the consequences of candidate actions, but it is unclear how much of the resulting gain c
- PaperRevisiting Smoothed Online Learning: Competitive Ratio, Dynamic Regret with Switching Cost, and Best of Both Worlds
We revisit smoothed online learning and develop algorithms with improved competitive ratios, optimal dynamic regret with switching cost, and best-of-both-worlds guarantee
- PaperTactix: Towards a Programmable Strategy Interface for Flexible SAT Solving
Modern SAT solvers combine a rich repertoire of proof rules with sophisticated strategies that determine when and how to apply them. Often, the internal implementations a
- PaperWAQS: Weight Absorption for Quadratic Probing and Affine Steering
Activation steering provides a lightweight alternative to fine-tuning for controlling large language model behavior. Existing methods, however, often face a trade-off bet
- PaperA Two-Stage Hybrid Framework for Inferring Air Trips from Mobile Location-based Service (LBS) Data under Incomplete Airport Sightings
Mobile device location-based service (LBS) data provide large-scale spatiotemporal observations that can help airport planners understand air travelers' mobility patterns
- PaperFlashMap: Flow Map Speculative Decoding
Speculative decoding accelerates large language model (LLM) inference by using a lightweight drafter to propose a block of tokens that the target model verifies in one pa
- PaperGazeAgent: VLM-Guided Implicit Gaze Calibration from Egocentric Multimodal Behavior for AI Glasses
AI glasses typically require explicit, user-specific eye-tracker calibration, and accuracy can drift when the device shifts during use. We present GazeAgent, a VLM-guided
- PaperHexagonal Basis Projectors for Model-Based Iterative CT Reconstruction
Image representation affects both the forward model and quantitative feature recovery in model-based iterative CT reconstruction. For isotropically bandlimited signals, t
- PaperCan Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin
To support sustained interactions and personalized assistance, agents use long-term memory to retain and combine user information across sessions. Reusing such memories c
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.