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
- PaperCARTA: Self-Supervised Reusable Transaction Embeddings via Heterogeneous Tokenization and Cross-Attention
Acquiring fraud labels for payment transactions is expensive and inconsistent across tasks, and high-cardinality identifiers such as merchant names make one-hot feature p
- PaperHow Well Can LLMs Verbalize Mathematical Formulas? A Multi-Domain Evaluation
Large Language Models (LLMs) have shown strong capabilities across natural language tasks. But their ability to generate accurate written verbalizations of mathematical f
- PaperSame Data, Different Bytes: Serialization-Invariant Integrity Checks for Agent-Published Datasets
Agent networks require reliable ways for requesting agents to verify where data is located, how it can be accessed, and whether the data received matches what the data ow
- PaperArctic-SWE: Revisiting the Long Horizon Agent Training by Modeling-System Co-Design
Long-horizon agent training, including software engineering, is advancing rapidly, but the recipe and infrastructure needed for a strong reinforcement-learning baseline r
- PaperGRaSP: Latency-Aware Optimization for Geo-Distributed Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) is increasingly served across geo-distributed cloud and edge infrastructures, where wide-area latency, cross-region egress cost, and
- PaperA Cross-Domain Evaluation of Prompting Techniques for Large Language Models
Prompt engineering has become a central mechanism for guiding the behavior of Large Language Models (LLMs) across a wide range of reasoning and language understanding tas
- PaperATLAS: Expert-Guided Sustainable Satellite Backhaul for Off-Grid Wildlife Monitoring
Remote wildlife monitoring increasingly depends on high-fidelity cameras and sensors deployed far from grid power and terrestrial networks. Low Earth orbit satellite link
- PaperA Symmetry-Matching Approach to Blind-Spot Reduction in Sparse Autoencoders
Language models can treat semantically distinct inputs as interchangeable at the representation level, creating blind spots that standard sparse autoencoder (SAE) objecti
- PaperCompositional Activation Steering Across Languages and Behaviors with Contextual Gates
Activation steering has emerged as an effective and precise way to influence the behaviours of language models. However, composing multiple steering directions to control
- PaperLeveraging Mental Models for Human-Centered Explanations: A Systematic Design Approach Illustrated by Explainable Fake Review Identification
Explainable AI (XAI) often prioritizes model fidelity over user intelligibility, yielding explanations that satisfy technical transparency yet fail to support human sense
- PaperHybridResearcher: Bridging the Structured-Unstructured Boundary for Deep Research Agents
While LLM agents are increasingly capable of gathering and synthesizing evidence from a single homogeneous source, such as structured tables or unstructured data, real-wo
- PaperPredicting Individual Differences in Lipreading From Eye-Tracking and Pupillometry During Silent Visual Speech
Lipreading ability varies widely, including among people who are hard of hearing. Although mouth-directed attention is linked to speechreading outcomes, it remains unclea
- PaperDistribution-Based Regularization for Reward Fine-Tuning Diffusion and Flow Models
Reward fine-tuning is an effective way to adapt pretrained diffusion and flow-matching models to downstream objectives, but aggressive optimization often leads to mode co
- PaperPeer Pressure: Execution-Verified Co-Evolution of Attacker and Defender Populations for Code Security
LLM code agents increasingly ship code with little oversight, yet defenders trained on static vulnerability datasets fall behind adapting adversaries. We co-train attacke
- PaperLastWords: Boring Problems Revisited
In 2022, the second author published a Last Words piece in Computational Linguistics in which he pointed out that, despite the advances in AI up to that point, there were
- PaperMulti-Speed Field Evaluation of a Semi-Autonomous Precision Sprayer for Weed Control in Vegetable Crops
Machine vision-guided precision spraying is promising for sustainable vegetable production by enabling site-specific weed targeting, reducing herbicide application while
- PaperScalable and Adaptive Distribution Regression via Random Features
Distribution regression seeks to learn mappings from probability distributions to response variables and has emerged as a unifying framework for kernel methods, multi-ins
- PaperQuery-Dependent Reading for Quantized Inner-Product Estimation: A Minimax Separation
We study quantization for inner-product estimation when storage and reading have separate budgets. In the static bit-probe model [Yao, 1981], an encoder stores $w$ bits a
- PaperMeasuring Data Diversity with Embeddings: A Taxonomy and Benchmark for Diversity Measures
Diversity is a critical property of text corpora, with direct implications for training data curation, test set design, and model generalization. However, its measurement
- PaperDo We Need the Largest LLMs for Every Clinical Decision?
Large clinical language models often require multi-GPU infrastructure, limiting local deployment. We introduce CERTA, a decision-level statistical certificate that determ
- PaperGoal Images Are Control Targets: Spatially-Grounded Goal-Image Synthesis for Robotic Manipulation
Goal-conditioned manipulation policies are steered by a goal image, a picture of the desired post-manipulation scene synthesized from the current observation and a langua
- PaperSample-Efficient Reinforcement Learning with General Utilities via Neural Dual Critics
Reinforcement learning with general utilities optimizes nonlinear functionals of policy-induced occupancy measures. We develop a natural actor-critic method for concave R
- PaperRAFT: Redundancy-Aware Input Filtering for Temporal Graph Neural Network Training
Temporal graph neural networks (TGNNs) have shown strong performance on dynamic graph learning tasks by continuously updating node memories from evolving interactions (i.
- PaperHow Intervention History Changes AI Agent Sabotage on Subsequent Tasks
AI control evaluations often reset agents' memory between tasks, although deployed agents may retain records of prior interventions. We ask whether learning that an earli
- PaperThe One-Pixel of Reasoning: One Truthful Relation Is Enough to Mislead LLM Agents
Can one sentence manipulate an agent's belief by targeting a single implicit warrant linking evidence to a conclusion? In this paper, we introduce the one-relation attack
- PaperThe Missing Compliance Class: LLM Graders That Collapse Jailbreak Success, and a Free Check
Jailbreak papers report an attack success rate, the share of responses that deliver the harmful request, and read it as a property of the target model. We hold the target
- PaperBellman Language Models: Solving the Recurring Decisions of LLM Agents
A general observation in agentic workflows, especially bounded ones, is that the decision space of the LLM, when we separate a decision from generation, starts approachin
- PaperDual Task Vector Merging: Leveraging Emotion and ASR Knowledge for Low-Resource Alzheimer's Disease Detection
Alzheimer's Disease (AD) detection from speech benefits from both paralinguistic and linguistic cues, yet model training is frequently constrained by limited data. Fine-t
- PaperSpriteStage: Long Horizon Animation Generation via Progressive Scene Programming and Replay
Video generation models synthesize visual sequences from text and image inputs. Extending video generation to long animations requires actions, dialogue, camera coverage,
- PaperFlowMaker: From Tasks to Cost-Efficient Generative AI Workflow Deployments
Generative AI workflows execute user tasks by composing sequences of LLM calls, where each call performs a sub-task (e.g., summarization or translation), forming a workfl
- PaperArbitrary-Scale Anisotropic 3D MRI Super-Resolution with Gaussian Prototypes
Reducing MRI acquisition time improves patient comfort, reduces motion artefacts, and increases scanner throughput. Clinical protocols often shorten acquisitions by sacri
- PaperLLM-Based Evaluation Planning for Heterogeneous Optimization
Heterogeneous optimization problems require an optimizer to decide not only which candidate solutions to evaluate, but also which objectives and constraints should be eva
- PaperLearning to Program Retrievals: Composing Search Primitives via Reinforcement Learning
Retrieval-augmented language models increasingly use multi-step search to solve knowledge-intensive tasks, yet existing systems typically expose retrieval through fixed p
- PaperMisleadQA: Diagnosing LLM Failures under Misleading Context
Large language models (LLMs) are widely used to answer questions from retrieved or user-provided context. However, provided context can be factually true yet out-of-scope
- PaperAn Impossibility Result for ETF Target Geometry, and an Equinorm Remedy for Imbalanced Analytic Continual Learning
Analytic continual learning (ACL) methods such as ACIL and GACL fit a ridge-regression classifier head on frozen features via the Sherman-Morrison-Woodbury identity, achi
- PaperPCHMR: Empowering and Benchmarking Human Mesh Recovery in Privacy-Constrained Real-World Settings
Fine-tuning directly on user-side data is an effective way to improve the performance of widely adopted data-driven human mesh recovery (HMR) models. However, doing so fo
- PaperA Statistical Viewpoint on Adam, Shampoo and Muon
We provide new statistical insights into designing stochastic optimization methods. By modeling the gradient via a normal distribution, we argue that the stochastic gradi
- PaperPattern-Driven Evaluation of LLM Code Optimization: Isolating Compiler-Transcendent Semantic Reasoning
Existing evaluations of LLM-based code optimization primarily measure end-to-end speedup, obscuring whether a model actually performs the intended optimization. For compi
- PaperMeasuring Consensus in AI Agent Networks
As AI agents become increasingly connected through networks and take on tasks that require negotiation and joint decision-making, a systematic approach is needed to asses
- PaperVTF900: A 900-Subject Visible-Thermal Face Recognition Dataset and Benchmark
Despite advancements in visible-thermal face recognition, where thermal probe (query) face images are matched against visible enrollment templates, existing benchmarks ar
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.