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…
Friday 16 October
- PaperOrTeN: Neural Inverse Graphics for Joint Terrain and Line-scan Camera Trajectory Reconstruction
Digital terrain maps (DTMs) are used for landing site selection, terrain-relative navigation, and geological analysis in planetary exploration. Existing state-of-practice
- PaperWho Verifies the Builder? Toward Independent Assurance for Agent-Produced Software
Coding agents can now implement a specification, write and run tests, repair failures, and declare the result ready for release. When the same agentic system produces bot
- PaperLearning to Correct Geometry in Generated Videos
Generated videos often lose geometric consistency under camera motion: structures warp under viewpoint change, parallax becomes inconsistent, and smooth camera movement m
- PaperWorld of SWECraft: Agent Collaboration at Scale via Simulated Software Worlds
As teams of AI agents take on larger projects and long-standing open problems, agent collaboration offers another dimension for scaling inference-time compute. To underst
- PaperRethinking the design space of Vanilla Pixel Diffusion Transformers
Pixel-space diffusion models have recently re-emerged as a compelling alternative to latent diffusion, avoiding the lossy latent bottleneck and separately trained autoenc
- PaperBehavioral Couplings: From Formation to Behavioral Emergence in Language Models
Fine-tuning large language models (LLMs) can induce behaviors beyond those explicitly targeted. For example, training a model to respond more warmly can make it more syco
- PaperAI-Driven Reproducibility and Analytical Robustness in Scientific Discovery
Reproducible and analytically robust research findings are essential to scientific progress, but evaluating these properties typically requires costly manual effort. We i
- PaperStopWatch: Goal Grounding for Object-goal Navigation
Pretrained VLMs bring rich world knowledge and semantic priors to object-goal navigation, and fine-tuning a VLM into a navigation policy has become a common recipe. Despi
- PaperDiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
Scientific discovery requires developing worthwhile hypotheses into practical investigations, yet learning from this evolving research process remains challenging. We int
- PaperGenerative Text Modelling and Language-Guided Visual Attention for Deciphering Palimpsests
Recovering obscured text in palimpsests, i.e. the manuscripts where the original writing (under-text) was erased and overwritten for reuse, is vital for preserving lost i
- PaperTask-aligned spectral inductive biases in parameterized quantum circuits
Parameterized quantum circuits are widely investigated in quantum machine learning, yet how their architecture can provide task-aligned inductive biases remains poorly un
- PaperBeyond the Answer: Student-Conditioned Trace Construction for Reasoning Distillation
A reasoning trace can accompany a correct answer without providing effective supervision for a particular student. We study how to construct traces that improve learning
- PaperWaiting Buys Exactly Two Moments: Endogenous Identification in Prediction-Driven Allocation
A planner with a fixed budget of preventive help must decide whom to help and when. Waiting reveals risk but removes intervention opportunities as higher-risk individuals
- PaperQuality-of-Transmission Estimation in Quantum Networks: Compute, Simulate, or Learn?
Future quantum networks will rely on control-plane decisions such as routing, scheduling, entanglement provisioning, purification, and memory allocation. Each decision de
- PaperSelf-Building Labs
Self-driving laboratories (SDLs) accelerate scientific discovery by automating experimental execution and optimization. AI agents can increasingly propose new experiments
- PaperENFR: Evidence Networks with Flow-Matched References for Amortized Simulation-Based Model Inference
The evidence, $\mathcal{Z} = p(x | \mathcal{M})$, of a data-generating model $\mathcal{M}$ is a powerful tool in Bayesian frameworks: it enables model inference, model mi
- PaperLearning without relearning physical symmetry: an SO(3)-equivariant convolutional network (CNN) on the sphere
Many of the most important datasets in the physical sciences live natively on the sphere, and these data often carry no preferred position or orientation. Using methods t
- PaperCocoRNA: Collective RNA Design with Cooperative Multi-agent Reinforcement Learning
Designing RNA sequences that reliably fold into specific secondary structures is essential for understanding their biological functions but remains a challenging computat
- PaperAcceptance Is Not Speed: Length Inflation in Training-Free Lossy Speculative Decoding
Speculative decoding typically characterizes speedup by draft tokens accepted per verification round. Lossless verification preserves the target model's output distributi
- PaperLearning Personalized Memory Gating from Delayed One-Sided Feedback
Long-term memory enables language-model agents to personalize future interactions, but a finite memory bank cannot preserve every extracted fact. Existing memory gating p
- PaperExplainable Machine Learning Analysis of Temperature Effects on Mechanical Strength of Fiber-Reinforced High-Performance Concrete
Predicting the compressive strength of fiber-reinforced high-performance concrete subjected to temperature exposure is challenging because to the intricate interdependenc
- PaperSteering beyond Language: Improving Multilingual Training-Free Text Embeddings via Paired-Residual Subspace Removal
While deriving text embeddings directly from frozen LLMs has emerged as a promising direction, existing methods focus almost exclusively on English, leaving multilingual
- PaperBeyond SAEs: Consistent Concept Discovery with Sparse Coding
Sparse autoencoders (SAEs) explain foundation model representations by decomposing activations into sparse combinations of learned dictionary atoms. However, the learned
- PaperTask-aware Kernel Stein certificates for Rényi differential privacy
Rènyi differential privacy, based on Rènyi divergence, has become a notion of choice for privacy guarantees. However, outside the Gaussian setting, Rènyi divergence can b
- PaperFuTransformer: FP8 prefill and INT4 decode for Llama-style inference on Hopper
Transformer prefill reuses weights across tokens and is dominated by matrix multiplication and activation data movement; single-token decode has limited reuse and is domi
- PaperPersistent Planar Memory for Video World Models
Video world models that generate and explore environments at scale need a persistent 3D memory of what they have produced. Plane primitives offer a natural candidate: a c
- PaperDrugHarness: An Evolvable Agent Harness for Computational Drug Discovery
Computational drug discovery requires agents to compose scientific operations and adapt to changing evidence and constraints. Here we introduce DrugHarness, an evolvable
- PaperThe Collection of a Real-World, Large-Scale Dataset for Automated Skill Evaluation in Central Line Dressing Change
Central line-associated bloodstream infections (CLABSIs) remain a major source of preventable morbidity and mortality in healthcare settings. Proper execution of the cent
- PaperParametric Resonance in Primal-Dual Learning for Slowly Non-Stationary Constrained MDPs
Primal-dual methods for constrained Markov decision processes are analyzed under a two-timescale assumption, with non-stationarity entering through two channels. In the a
- PaperDLite: History-free Speculative Decoding for Agentic AI
Speculative decoding has become a mainstream technique for accelerating large language model (LLM) inference by using a lightweight draft model to generate candidate toke
- PaperSampling the XY model with an attention-based neural network
We present a transformer-based variational autoregressive network for sampling lattice systems with continuous degrees of freedom and apply it to the two-dimensional XY m
- PaperToolRosetta: Surface-Form Invariance of Tool-Call Guards
Step-level guards for tool-using agents are evaluated on tidy JSON tool calls, but deployed coding agents act through execute_bash and execute_code tools whose payloads a
- PaperMesoscopic learning dynamics of extensive-width neural networks
Understanding how stochastic gradient descent learns internal representations in wide neural networks trained on rich target functions is a central problem in machine lea
- PaperVideo Diffusion Avatars: Taming Video Diffusion Models into Controllable 3D Avatars
Video diffusion models (VDMs) trained on internet-scale data encode a rich prior on appearance, motion, and physics that is difficult to replicate with explicit 3D render
- PaperLLM-Assisted Bi-Approximate CHC Solving
Constrained Horn clause (CHC) solvers often struggle to discover deep counterexamples whose derivations may require extensive rule unfolding. Although large language mode
- PaperLogic-Guided Graph Denoising Diffusion Models
Graph diffusion models are competitive approaches for generating complex graph-structured data. However, when such distributions have strict structural constraints, diffu
- PaperUniversal Semantic Enhancement for Weakly Supervised Anomaly Detection
Weakly supervised anomaly detection on tabular data is an essential task in many label-scarce applications, since tabular data is widely encountered and it is commonly ob
- PaperIRAH: Hierarchical Agentic Tree Search for Retrieval Pipeline Optimization
Optimizing Information Retrieval (IR) pipelines for Retrieval-Augmented Generation (RAG) requires jointly selecting structural components and numerical hyperparameters un
- PaperFrom Flow-Box Invariants to Global Conservation Laws: Machine Learning-Assisted Detection of Singularities and Near-Integrability
Conservation laws reveal invariant structure in dynamical systems and constrain their evolution to lower-dimensional level sets. Locally, however, per the flow-box theore
- PaperA Paired RGB-Sonar Dataset for Fish Monitoring with Consumer Sonar
Imaging sonar enables underwater observation in conditions where optical imaging is ineffective due to darkness and turbid water. However, imaging-sonar systems previousl
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.