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…
Tuesday 20 October
- PaperManifold-Informed Neural Networks for Low-Label ECG Electrolyte Inference
Physics-informed neural networks (PINNs) supervise on the residual of a known differential operator. Many high-stakes inference problems admit no such operator: clinical
- PaperStabilizing Filters for Graph Signal Generation
Generating graph signals is an important task in machine learning, and incorporating the underlying graph into a generative model enables structurally-informed distributi
- PaperABACUS: A Benchmark for Image Editing Models to Assess Object Category and Counting Under Scene Conservation
Instruction-based image editing models can now add, remove a specified number of objects or change their category while preserving the scene. Yet these models often fail
- PaperDisclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent Memory
Large language model (LLM) agents increasingly use persistent memory to personalize responses, and personal attributes in this memory pose a privacy risk if exposed. We a
- PaperDebiased Prior-Data Fitted Networks for Amortized Bayesian Semi-Parametric Inference
Prior-data fitted networks (PFNs) have recently gained popularity as an end-to-end approach to amortized Bayesian inference. Yet, their statistical behavior for semi-para
- PaperTowards Consistent Geospatial Representations: Aligning One Encoder to Many Foundation Models
Geospatial foundation models (GFMs) differ widely in pretraining objective, modality and resolution, and none leads across benchmarks. We ask whether their representation
- PaperFrom Abstraction to Action: DSLs for Natural Language Abstraction Interpretation and Execution
Natural-language instructions often rely on high-level abstractions, such as asking an agent to ``stack blocks in a pyramid.'' Interpreting abstract instructions requires
- PaperRecommending Bacterial Cultivation Conditions from 16S rRNA
Recommending bacterial cultivation conditions from sequence data is a challenging structured problem characterized by missing standardized benchmarks and limited use of s
- PaperReward Misspecification Degrades Chain-of-Thought Monitorability
Monitoring the chain-of-thought (CoT) of language models (LMs) is a key strategy for detecting and preventing misbehaviors for AI safety. As such, it is critical to ident
- PaperLearning Normal Coordinates on Riemannian Manifolds with Flow Charts
Riemannian manifolds are powerful models for problems with non-Euclidean structure. Recent work in geometric machine learning has focused on training deep neural networks
- PaperAdaptive Replay Refinement: Allocating Test-Time Compute Between Revision and Resampling
Test-time scaling allocates additional inference compute to refining existing solutions or generating new ones. This raises a fundamental question: Should I keep improvin
- PaperAGGR-Mamba: Mamba-based Network with Attention-Guided Gated Residual Refinement for Undersampled MRI Reconstruction
Undersampled magnetic resonance imaging (MRI) reconstruction aims to recover high-quality images from partially acquired k-space data, thereby reducing scan time. However
- PaperCPVB-RG: Cross-Prior Visual Bridging for Prior-Aware Chest X-Ray Report Generation
Radiologists interpret follow-up chest X-rays by comparing current and prior examinations to identify new, resolved or progressing findings. Most report generation system
- PaperLocal Work, Global Progress: A Convergence Theory of AI Agent Collaboration
Teams of large language model (LLM) agents are increasingly applied to complex tasks, but their collaboration protocols are mostly designed empirically, without convergen
- PaperHRoPE: Homography Relative Positional Encoding
Geometric Relative Positional Encoding has become the primary mechanism for injecting spatial inductive biases into multi-view transformers. Existing designs condition at
- PaperChartEvo: Self-Evolving Agent Harnesses for Long-Tail Chart Reasoning
Multimodal large language models (MLLMs) have substantially advanced chart understanding and reasoning, yet their performance remains highly uneven across chart types. Wh
- PaperForty Questions: Identifying a Language Model from One-Word Answers
A model behind an API can be identified from its one-word answers to everyday questions such as "Name a sound" or "Name a poet". A model's profile records how often it gi
- PaperGALA: Geometry-Aware Language Model for Controllable Object Arrangement
Reasoning about fine-grained placement constraints, such as support and containment, is essential for realistic 3D scene creation. It remains a significant challenge for
- PaperHow Language Models Learn Taste: Brand Preference in LLMs
Asked to name a running shoe brand, language models say Nike. Asked to recommend one, they say Brooks. This paper asks where models learn that taste. Across 102 models an
- PaperVGL-stGen: Learning a shared multimodal model for lung histology and spatial transcriptomics
VGL-stGen is a multimodal large language model adapted from a pretrained medical vision-language model using paired lung H&E and spatial transcriptomics with single-cell
- PaperPI-MLLM: Psychophysics-Inspired Multimodal Large Language Model for Oddly Satisfying Video Emotion Analysis
Oddly Satisfying Videos (OSVs) can evoke strong viewer responses through repetitive motion, visual tactility, and ASMR-like sounds despite containing few explicit semanti
- PaperReliability-Aware Reconstruction of V-Shaped Surfaces with a Low-Cost Multi-Zone SPAD Sensor
Low-cost multi-zone single-photon avalanche diode (SPAD) sensors provide compact time-of-flight measurements but are limited by sparse sampling and unreliable depth estim
- PaperSplatFlux: Feed-Forward 4D Gaussian Reconstruction and Generation from Video Latents
This work presents SplatFlux, a feed-forward latent-to-4DGS framework for both video-based 4D reconstruction and conditional 4D generation. Our key observation is that ob
- PaperGeometry-Aware Block Selection for Sparse Variational Gaussian Processes
Sparse variational Gaussian processes (SVGPs) are a widely used, principled approach to scalable Gaussian process modelling. Their success stems from their theoretically
- PaperConvergent Performance, Divergent Mechanisms in LoRA-Adapted Vision Foundation Models for Brain MRI
Adapting Vision Foundation Models (VFMs) to medical imaging via LoRA has become standard practice, yet model selection is guided almost entirely by downstream task metric
- PaperTPO: Tri-level Distributionally Robust Learning for OOD Direct Preference Optimization
Direct Preference Optimization (DPO) minimizes empirical risk over observed preference comparisons, implicitly assuming that the training preference distribution matches
- PaperLocal Inference of LLMs on Long Contexts: A Data Systems Perspective
Large language models can solve complex problems across a variety of subjects, such as mathematics and coding. For such complex analytical tasks, models with a long conte
- PaperCan Language Models Get "Aphasia" From Neuronal Ablation?
Progressive neuronal loss is the hallmark of neurodegenerative disease, yet how loss of neurons shapes the pattern of cognitive decline remains poorly understood. Here we
- PaperExeBench-FHD: Addressing Fidelity Issues in Decompiler Evaluation
ExeBench is one of the most widely used benchmarks for evaluating LLM-based decompilers. We analyze ExeBench and identify nine issues that affect how faithfully a test me
- PaperRegion-Guided Food-Package Evidence Extraction and Abstention-Aware Draft R3337 Screening with Selective VLM Review
Applying South Africa's draft R3337 warning criteria to food-package photographs requires nutrition, ingredient and product-form evidence. This study presents a region-gu
- PaperLearn to Modify: Self-evolving Multi-agent Refinement Framework for Conversational Text-to-Motion Generation
Despite rapid progress in text-to-motion generation, existing methods are commonly designed for single-shot generation. When users are dissatisfied with specific motion d
- PaperJAXbounce: A Continuous-Control Pong-Like Benchmark for Active Inference Beyond Low Dimensional Environments
We introduce JAXbounce, a continuous control pong-like benchmark designed to evaluate active inference beyond discrete, low dimensional environments. JAXbounce combines c
- PaperMaD-RSI: Model-as-Data for Recursive Self-Improvement of Agent Harnesses
Recursive self-improvement (RSI) of agent harnesses has emerged as an effective approach to enhancing the capabilities of large language model (LLM) agents. By searching
- PaperParameter-Efficient Adaptation of Time Series Foundation Models for Electrical Load Forecasting
Accurate electrical load forecasting supports power-system operation across countries, regions, cities, and buildings, but repeated development of target-specific models
- PaperReframing Object-Centric Reinforcement Learning: From Absolute to Relative Representations
Object-centric reinforcement learning agents typically receive each object's position in a fixed global frame, even though their decisions usually depend on where objects
- PaperAttractive Faces Skew Text-to-Image Reward Models and Leaderboards
Human preference is now central to the evaluation, guidance, finetuning, and ranking of text-to-image models. However, the susceptibility of human preferences to bias in
- PaperAdaptive Pullback: Reweighting Supervision at Penalty Jumps in On-Policy Distillation
On-policy distillation (OPD) supervises student-generated responses using sampled-token student-teacher log-ratios. A positive log-ratio penalizes a token that the studen
- PaperOffline Makes Online Better: Calibrated Cache Compression for Video Generation
Token merging is an effective approach to reducing KV-cache memory consumption in autoregressive video generation by clustering temporally redundant tokens and retaining
- PaperUnified RAW Image Exposure Correction and Restoration via Linear Illumination and Frequency-Adaptive Enhancement
Incorrect exposure degrades both image brightness and recoverable scene detail. Existing sRGB-based correction methods are limited by the non-linear image signal processi
- PaperCrossFit-GS: Out-of-Fold Pose Estimation for COLMAP-Free 3D Gaussian Splatting
Pose-free 3D Gaussian Splatting (3DGS) aims to bypass cumbersome Structure-from-Motion (SfM) by directly reconstructing scenes from unposed image sequences. In this work,
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.