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
- PaperChronoSheaf: Joint Spatio-Temporal Spectral Filtering on Cellular Sheaves
Sheaf neural networks generalize graph neural networks by assigning each edge a learned linear restriction map that specifies how the local representations of adjacent no
- PaperSelectPFN: Amortized Bayesian Variable Selection for Sparse Nonlinear Regression with Prior-Data Fitted Networks
Tabular foundation models based on prior-data fitted networks (PFNs) predict on a new data set in a single forward pass, but they cannot report which inputs their predict
- PaperFollowing Delegation Traces to Study Human Oversight in Interaction with Multimodal AI
As multimodal AI systems are becoming our everyday thought partners, the shift towards studying how users transfer control to these systems becomes especially urgent. In
- PaperLearning Speech Attribute Representations via Multi-Teacher Distillation
Recent post-training approaches have shown that self-supervised speech encoders can be adapted to learn a single utterance-level speech attribute through knowledge distil
- PaperAgentic-Priors: Using Large Language Models to Address the Cold Start Problem in Preference Elicitation
An agent that learns a user's preferences from their choices faces a cold start problem: before any choices are observed, it must rely solely on a prior. Informative prio
- PaperFlow-CLIP: Image-Conditioned Residual Scoring for CompositionalImage-Text Matching
Vision--language pre-training has enabled substantial progress in image--text retrieval and zero-shot recognition by learning transferable cross-modal representations. Ho
- PaperThe Lagrangian Structure of Cost-Penalized Active Feature Acquisition
Active Feature Acquisition (AFA) sequentially selects features to maximize predictive accuracy under an acquisition budget. A natural heuristic greedily maximizes Expecte
- PaperBridgeAfford: Bridging Query-Target Gap for Generalizable 3D Affordance Grounding
Language-guided 3D affordance grounding aims to localize functional regions on 3D objects according to interaction intents. However, existing methods exhibit poor general
- PaperCodeHealth Predicts the Token Cost of Agentic Code Review: A Pre-Registered Study of 465 Agent-Authored Pull Requests
Context: Organizations increasingly delegate code review to multi-agent large language model (LLM) pipelines billed per token. Low code quality raises human maintenance e
- PaperLearning Rewards in Strategic Games
Understanding the objectives that drive agents' behavior is crucial in strategic environments, where multiple agents interact and adapt to one another. This challenge ari
- PaperCoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness
As Vision-Language Models (VLMs) advance, they are increasingly expected to perform spatiotemporal reasoning over motion, actions, and view changes beyond what the input
- PaperThe Tilted Sampling Problem: Optimism, Posterior Sampling, and Logarithmic Regret
Many modern learning systems are used not to select a single best action, but to sample diverse high-quality outputs. Examples include entropy-regularized reinforcement l
- PaperSeeing is Believing: Benchmarking and Mitigating the Interference of Language Priors on Visual Perception in MLLMs
Language priors in MLLMs can override visual evidence, impairing visual perception. Existing benchmarks assume shared priors across models and rely solely on accuracy. Ho
- PaperIn-Context Learning Before Specialisation: Theory of Learning in a Solvable Topic Model
Sequence models can generalise in fundamentally distinct ways: extrapolating structures seen in training, or using their prompt to adapt to novel tasks. The prevailing st
- PaperTEM: Temporal State Tracking Memory for Large Language Model Agents
An agent's memory must remain useful as information changes across conversations. A new fact may replace an earlier value without making that value irrelevant to a later
- PaperSelf-Calibrated Subspace Robust PCA for Parameter-Free Removal of Mixed Noise and Line Stripes in Hyperspectral Images
Hyperspectral images (HSIs) are often corrupted by Gaussian noise, impulses and stripes whose intensities vary across bands. The representative coefficient correlated tot
- PaperSurgStreamer: proactive, request-driven monitoring of surgical video streams with structured state and a reusable reasoning layer
Surgical teams could benefit from assistants that watch the video for requested events, such as "tell me when the clip applier appears during Calot triangle dissection",
- PaperRank Measures of Fine-Tuning Updates Need a Noise Baseline
Studies of what fine-tuning does to a language model often summarise the weight update $ΔW$ by its rank. We compare the rank measures used for this against the same measu
- PaperGraph Dirichlet Energy for Fitting-Free Bivariate Causal Inference
We propose the Graph Dirichlet Energy Causal Inference (GDECI) criterion for distinguishing cause from effect in bivariate settings. For a candidate direction $X\to Y$, w
- PaperAnvil: Scaling Embodied Spatial Intelligence through Knowledge Recirculation
Embodied spatial intelligence requires more than visual recognition: models must localize entities, reason about their relations, and express this knowledge in action-rel
- PaperLearning Lean Feedback for Efficient Proof-Candidate Evaluation on GPUs
Training language models for formal theorem proving requires large numbers of verifier calls. Slow checks and timeouts often leave GPUs waiting and withhold rewards from
- PaperProvably Efficient Risk-Sensitive Offline Reinforcement Learning via Optimized Certainty Equivalents
Risk-sensitive reinforcement learning (RL) addresses decision-making under uncertainty and adverse outcomes. Learning risk-sensitive policies from fixed datasets is impor
- PaperLethe: Link Inference Attacks For Evaluation of Edge Unlearning Methods
Graph Unlearning (GU) aims to remove the influence of specific training data from a Graph Neural Network without retraining anew. While most methods address removal of no
- PaperFrom Sketch to Scene: Relightable Garment Reconstruction from Marked Sketches
Sketching is one of the most natural ways for people to express visual ideas. Unlike the text prompts that most generative systems rely on today, a sketch captures spatia
- PaperDynamic ordering in sequence generation in Transformers: experiments on low-resource Tagging scenarios
This paper introduces TagInsert, a Transformer-based model that challenges the common left-to-right (L2R) generation paradigm in Transformers, for sequence labelling task
- PaperCausal Spatio-Temporal Neural Distance Fields for Counterfactual Cardiac Anatomy
Counterfactual cardiac anatomy can support risk modelling and intervention planning, by predicting how a patient's heart would change under altered clinical conditions. H
- PaperSeeing Both the Forest and the Trees: Reusing Holistic 3D Priors for Part-Decomposed Generation
Generating 3D assets with explicit parts requires two properties at once: geometric detail inside each part and structural coherence across the whole object. Recent image
- PaperTemporal Periodic Image Registration with Implicit Neural Representations
Implicit Neural Representations (INRs) have recently gained popularity for their ability to model functions using simple and lightweight networks. These methods have also
- PaperPhysics-Aware Distillation of a Grid Foundation Model for Real-Time Edge Inference
Grid foundation models (GridFMs) are graph transformers pretrained on a masked power-flow objective, and evaluate power flow orders of magnitude faster than an iterative
- PaperLocal Epochs as Optimal Stopping: Theory and Evidence in Federated Learning
How long should each client train before communicating? Federated learning usually answers with a fixed, hand-tuned number of local epochs, yet an extra epoch helps only
- PaperCompiling Multi-Threshold Operators for Quantized Non-Monotonic and Fine-Granular Activations in Custom-Tailored DNN Accelerators
Aggressive quantization of neural networks can expose activation functions as bottlenecks for efficient hardware acceleration. Implementing quantized activations as multi
- PaperA Closed Form Depth-Width Law for Neural Collapse in Deep Linear Networks
How depth and width of neural networks shape learned representations is usually studied only after training. We show that, in a tractable feature-learning setting, this d
- 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
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.