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…
Monday 19 October
- PaperLook Before You Reason: Implicit Visual Thinking for Efficient Multimodal Reasoning
Vision-language models (VLMs) have advanced rapidly in multimodal reasoning, yet they remain limited on tasks requiring fine-grained understanding of small or easily over
- PaperAutomated Brick Schema Knowledge Graph Completion Across Buildings
The Brick schema represents building equipment, sensors, spaces, and the relationships between them as typed, multi-relational graphs, providing machine-readable metadata
- PaperModeling Authentic Research Trajectories: A Graph View of Research Ideation
The research idea in a published paper is rarely the project's initial idea. Between the two lies a closed-loop process in which researchers run experiments, derive insig
- PaperEMBER: Predicting TCR--pMHC Binding Without a Docked Complex
We propose EMBER, a structure-based framework for TCR--pMHC binding prediction that eliminates the need for a predicted docked complex, and with it the placement error th
- PaperUnsupervised Tool Evolution for Coding Agents in Data-Lake Analytics
Coding agents can answer analytical questions over a data lake by discovering, cleaning, and joining the relevant data. However, they discard this work after each questio
- PaperSteering Vision-Language Models for Visual-Contextual Privacy in Location Disclosure
Vision-language models (VLMs) can infer sensitive information such as geolocation from subtle visual cues, creating privacy risks when responses disclose more detail than
- PaperVampPrior Unleashed
Deep latent variable models (DLVMs) underpin many modern analysis pipelines, for example in single-cell genomics, yet their prior distributions have received markedly lit
- PaperPhysics-Inspired Optimizers beyond the Edge of Stability: Period-Two Orbits and Delayed Instability
Gradient descent with momentum can be viewed as a particle moving with friction in the loss landscape. In deep learning the learning rate is usually large, so training is
- PaperWhat Not to Erase: Saliency-Constrained Augmentation for Low-Resource Handwritten Character Recognition
Optical Character Recognition (OCR) and handwritten character recognition (HCR) in low-resource historical material collections often rely on data augmentation, yet augme
- PaperEvolving Self-tuning Benchmarks for Long-Horizon Tool Use
For AI assistants to move beyond simple chat interfaces and reliably assist users with applications like Gmail, Venmo, and Slack, we need to improve their tool-use capabi
- PaperWhen Does an Added Planning Capability Create Operational Value? An Observable Evidence Standard
Industrial artificial intelligence (AI) planning systems combine predictive models, optimization logic, controls, and governance rules, but improvement in the complete po
- PaperGlobal Security Blind Spots: Translation as a Safety Bypass in Low-Resource Languages
Large language models are deployed globally, yet safety alignment and evaluation remain concentrated in English: harmful requests refused in English can elicit unsafe com
- PaperEvaluating Context Compaction on the Questions That Come Later
Language-model agents compact their context for the question at hand, but the compacted context must also serve questions that come later. We evaluate compaction on these
- PaperGeneralizing Multimodal Foundational Models in Context-Driven Class Incremental Learning
Class-Incremental Learning (CIL) aims to learn new classes continuously without forgetting the previously learned ones. Recent works in CIL have significantly advanced ac
- PaperStronger artificial intelligence breakthroughs hasten their own exhaustion
Progress in artificial intelligence is widely assumed to scale with effort: more researchers, papers and investment should accelerate discovery. Theories of technological
- PaperRealControlBench: A Benchmark for Interpretability-Informed Fine-Grained Control of LLMs and Agents
Existing steering benchmarks are built around simplified, isolated generation tasks and evaluate a single behavioral attribute under controlled settings that do not refle
- PaperVulnerability Analysis for Safe Multi-Agent Reinforcement
Safe Multi-Agent Reinforcement Learning (SMARL) aims to learn cooperative control policies under prescribed safety constraints. Al- though existing SMARL methods focus on
- PaperTEX: Test-Time Scaling Testing Agents via Execution-based Cross-Validation
Test-case generation is critical but remains challenging for language models. Existing test-time scaling methods either isolate candidates or aggregate traces, which do n
- PaperWhen Does Hate Transfer? A Large-Scale Study of Cross-Lingual Hate Speech Detection
Effective detection of hate content is essential for maintaining healthy online communities, yet performance can vary substantially across languages. This work investigat
- PaperVPFlow: Value-Predictive Planning with Imperfect World Models for Offline Goal Reaching
Offline goal-conditioned reinforcement learning enables skill acquisition by reaching any goal from any state without dense rewards. Model-based methods allow for plannin
- PaperA latent control model for realistic rodent motion
The development of embodied models of animal behavior is a major goal of the neuro-AI community. Embodied models will enhance our ability to make direct comparisons betwe
- PaperWhat Would Removing This Corruption Change? Failure Attribution for Vision-Language-Action Models
Vision-language-action (VLA) models are sensitive to visual corruptions, but knowing that a corruption is typically harmful does not establish whether removing it would b
- PaperOn Maximum Clique and Maximum Consensus Formulations in Point Cloud Registration
Maximum clique and maximum consensus are widely used formulations for robust point cloud registration in robotics. Maximum consensus seeks one transformation that aligns
- PaperFLINT: Fixed-budget Late Interaction
Multi-vector retrieval models such as ColBERT often outperform single-vector models of comparable scale by matching queries and documents at the token level. However, ret
- PaperCertifying Repeatable Entry-Replay Witnesses for COBOL-to-Java Migration
Producing synthetic data for comparison testing a migrated COBOL application is a major challenge that agentic migrations face today. Our prior paper, the Agentic Method
- PaperAfrican Languages AI Safety Readiness Report
With the widespread adoption of large language models (LLMs) across languages and domains, AI safety has emerged as a critical global concern. However, due to resource co
- PaperAuditing Safety Preference Supervision with Recorded Derivations
Preference labels align model training, but the judgments behind them are difficult to inspect or verify. In this paper, we examine how preference construction can be che
- PaperSolving the Ho--Nguyen Conjecture for Gaussian Mixtures: Applications to Mixtures of Experts
Over-fitted Gaussian mixtures can contain many parameter configurations with nearly the same density, making the order of density cancellation central to their parameter-
- PaperTheorem prover Arend
This paper is an exposition of the theorem prover Arend developed at JetBrains Research. Arend language has been designed to facilitate the formalization of mathematics w
- PaperGuided Diffusion for Trustworthy Synthetic Text Generation
The rapid evolution of Large Language Models is fueled by massive datasets, yet this reliance poses severe privacy risks, as models can inadvertently memorize and even di
- PaperWhen Models Know but Can't Linearly Say: Relational Encoding Limits Linear Vulnerability Classification in Code LLMs
Large language models can detect vulnerable code, yet the form of vulnerability encoding in their representations remains unclear. We analyze 8 code models spanning 6.7B-
- PaperTxnQA: Benchmarking Analytical Reasoning and Evidence Grounding over Transaction Event Sequences
Analyzing merchant transaction histories requires dynamic temporal filtering, entity resolution, and aggregation over irregular event streams--operations poorly captured
- PaperValiAssist: Scaling LLM-generated Programming Feedback Validation by Demonstration
Generative AI can create programming feedback at scale, but validating its alignment with instructors' pedagogical goals and strategies remains challenging. Instructors m
- PaperTarget-Aware Curation of Hallucination Stress Tests for Large Language Models
Hallucination stress tests can yield similar average scores across language models even when different prompts elicit hallucinations in each model. We develop a procedure
- PaperDiagnostic Analysis for Large Language Model Reasoning
Reasoning structures (e.g., chains and graphs) are increasingly used for probabilistic inference, factuality verification, and uncertainty estimation, but their structura
- PaperAutoRedClaw: Automated Red-Teaming for Claw-Style Agents
Agent systems are shifting from task-scoped tool-use agents to persistent, personalized assistants such as OpenClaw. These claw-style agents maintain configuration files
- PaperPredicting Linear Relational Decodability Without the Relation
Linear relational embeddings (LREs) approximate a language model's subject-to-object mapping with an affine function. Their faithfulness varies enormously across relation
- PaperCEFR-oriented Russian Text Simplification Using Reinforcement Learning
We present a study on controlled automatic simplification of Russian texts using preference-based optimization algorithms with a focus on adapting texts to the A1, A2 and
- PaperEGI-BENCH: An Enterprise General Intelligence Benchmark Suite
Enterprise adoption of LLMs in agentic workflows is gated by evaluations that span a wide arc of abilities: CRM operations, heterogeneous-document retrieval, personal dat
- PaperMMedAgent-Plus: Scaling Multimodal Medical Agents across Modalities, Tasks and Workflows
Medical workflows often require multiple interdependent analyses, but existing specialist and generalist AI models are not designed to coordinate them. We introduce MMedA
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.