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
- PaperJoint Constraint Aggregation for Qualifier-Sensitive Retrieval-Augmented QA
Retrieval-augmented QA can fail even when the correct answer is in the retrieved evidence. This can happen when a competing answer satisfies some, but not all, of the que
- PaperMatchCityLoc: Aerial Localization in LoD City Models via Surface Normal Matching
Autonomous Unmanned Aerial Vehicle (UAV) navigation in urban environments requires precise pose estimation. Because Global Navigation Satellite System (GNSS) signals are
- PaperBeyond Two Tracks: Speaker-Anchored Full-Duplex Dialogue Recovery
Spoken interaction is moving from alternating turns to full-duplex conversation, where an agent listens while speaking. Learning this coordination requires natural dialog
- PaperCounting Contributions, Not Views: Occlusion-Aware Densification for 3D Gaussian Splatting
3D Gaussian Splatting grows a dense scene from a sparse initialization through adaptive density control (ADC), driven by per-Gaussian statistics gathered during rendering
- PaperRGH-GNN : Risk-Gated Heterogeneous Graph Neural Network for Financial Fraud Detection
Credit card fraud is a significant problem for financial institutions, resulting in substantial monetary loss each year. Fraud patterns and methods are continuously evolv
- PaperThis is SParTA: A modular, efficient and scalable transformer architecture for jet-tagging
We present the Sparse Particle-interaction Transformer Architecture (SParTA), a modular, scalable, and efficient transformer for jet tagging at high-energy colliders. Exp
- PaperLVMem: Image-Augmented Memory for Long-Horizon Question Answering
Reliable language-guided perception is essential for embodied agents, where questions about objects, events, and their locations must be answered from long observation hi
- PaperOmni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs
Recent Omni LLMs (OLLMs) have demonstrated remarkable capabilities in joint audio-visual reasoning, yet cross-modal hallucinations remain a major challenge. Existing miti
- PaperLOB-Impact Benchmark: Emergent Market Impact in Generative Limit Order Book Models
Realistic market impact is essential for generative limit order book (LOB) models to serve as world models for trading agents. If a simulator misprices this mechanism, ag
- PaperA general-purpose System One decision model for clinical records
Clinical care, health-system operations and biomedical discovery depend on extracting reliable answers from patient records, yet applying diverse clinical questions acros
- PaperSciFigBench: A Benchmark for Scientific Method Figure Understanding
Scientific method figures often provide researchers with a clear visual entry point into a paper's methodology and core contributions, yet their dense layouts and complex
- PaperClockMark: Adaptive and Host-Dependent Watermarking for Large Language Models
Large language model (LLM) watermarking operates on the next-token distribution that evolves during generation. In streaming generation, each sampled token becomes part o
- PaperLEAF: LUT-aware Efficient Attention on FPGAs
We introduce Lookup-table (LUT)-aware Efficient Attention on FPGAs (LEAF). LEAF is the first nanosecond-scale LUT-aware transformer for FPGAs. Deploying transformers that
- PaperBUMP: Body-driven Unified Multi-object Physics for HOI Synthesis
Generating human-object interactions (HOIs) with multiple objects is challenging because the resulting motions arise from different underlying causes. Human motion reflec
- PaperGraph Neural Networks for Astrophysics and Cosmology
Physics seldom makes breakthroughs when we consider objects only in isolation. Instead we model and measure how objects sit among their neighbours, spatial, temporal, or
- PaperText-to-Image Generative Modeling Without Language Pretraining
Modern text-to-image (T2I) systems use internet-scale language pretraining for text-conditioned image generation. We ask whether language pretraining is necessary for str
- PaperOpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory
Multimodal large language models (MLLMs) have made rapid progress on visual reasoning, yet many tasks require evidence that is difficult to obtain through internal reason
- PaperCan It Actually Work? Synthesizing Functional CAD Mechanisms
While LLM agents can generate visually plausible CAD assemblies, these designs often fail to fulfill their intended physical functions. We study functional CAD design, a
- PaperReinforcement Learning with Visually Attributable On-Policy Self-Distillation
Multimodal reinforcement learning with verifiable rewards (RLVR) provides reliable task-level supervision, yet offers limited guidance for localizing errors in visual rea
- PaperVideoMaMa++: Temporally Consistent Video Matting via Preserve-and-Refine Token
Diffusion-based video matting has recently emerged as a leading approach, leveraging video diffusion priors from internet-scale pretraining to achieve strong zero-shot ge
- PaperVitronEdit: Universal Visual Editing across Images, Videos, and 3D Scenes
Recent advances in unified visual editing have begun to consolidate image and video editing within a single model, while 3D scene editing remains largely separate and con
- PaperRopedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience
World models enable embodied agents to anticipate action consequences, yet jointly modeling locomotion and manipulation across diverse embodiments remains challenging due
- PaperInfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation
Procedural generation plays a key role in synthetic data creation and game development, offering greater controllability, editability, and diversity than static mesh repr
- PaperCoopUQ: Robust Multi-Robot Social Navigation via Uncertainty-Aware Cooperative Forecasting
Reinforcement learning enables mobile robots to make fast and scalable navigation decisions in constrained human-shared environments. However, directly extending single-r
- PaperManga2Animate: An Agentic Framework for Faithful Manga Animation with Script and Storyboard Planning
Adapting existing manga into coherent animation that stays faithful to the source is a valuable yet challenging task. Existing methods either access the manga mainly thro
- PaperGenOlympiad: Benchmarking Frontier Image Models at Their Capability Boundaries
Text-to-image models have made tremendous progress and can produce high-quality images. However, a question which would be asked in any other discipline is where the fron
- PaperWhere is Physical RSI capability from? An Observational Scaling Law of LLM-as-policy
In this paper, we systematically investigate the mechanisms, scaling behavior, and generalization of physical Recursive self-improvement. We introduce PhysRSI-eval to qua
- PaperWeAct: Dynamic Weight Switching as Agent Actions
Long-horizon agents must learn heterogeneous capabilities from interleaved trajectories. Updating shared parameters to learn new capabilities can degrade previously acqui
- PaperTrain An Imaginative Agent
A seemingly reasonable push in Sokoban can make the puzzle unsolvable. To avoid such mistakes, an agent has to anticipate the consequences of its actions before execution
- PaperAnyGoal: On World Model Generalization Beyond Expert Rollouts
The goal of a world model is to capture the dynamics of an environment. This has the great appeal that it allows agents to plan and simulate a course of actions with the
- PaperLatComm: Reusable Context Compression for Latent Communication between Large Language Models
Systems that combine several large language models (LLMs) often use one context for many questions. When the context is passed between models as text, the receiving model
- PaperNewton-Based Methods for Bilevel Optimization Beyond Lower-Level Strong Convexity
Bilevel optimization provides a framework for machine learning tasks such as hyperparameter optimization, data reweighting, and meta-learning. Existing Newton-based bilev
- PaperDiscrete Neural Interlingua for Ontology-Agnostic EHR Modeling
EHR foundation models promise scalable clinical prediction across health systems, yet their deployment is constrained by a tokenization bottleneck. The same clinical conc
- PaperSpecKCast: Spectral Kalman Forecasting for Diffusion Acceleration
Diffusion Transformers (DiTs) achieve high-fidelity image and video generation, but they suffer from substantial inference costs due to repeated transformer evaluations a
- PaperSame Simulation, Different Evidence: Where Retrieved Tool Output Costs LLM Agents Accuracy
LLM agents that compute the right answer can still answer wrongly. Agent harnesses increasingly keep long tool outputs out of the context window, saving them to files tha
- PaperKronecker Delta Rule for Long Context Linear Attention
We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for associative matrix memories. KronLSTM extends the xLSTM fa
- PaperSupervised Learning with Quantum Hamiltonian Embeddings
Machine learning is widely regarded as a promising application in which quantum computing could offer a computational advantage. However, general quantum machine learning
- PaperCompeting Learning in Hybrid Architectures
Many modern language models have adopted hybrid architectures that incorporate both linear-time recurrence and softmax attention. Modern recurrence layers provide a highl
- PaperProteinGeoBench: Frontier Structural-Biology Agents Are Fluent at Lookup but Lost in Geometry
Frontier agents retrieve structural metadata well and compute geometry from coordinates less reliably. We ask how much of a benchmark score reflects that gap and how much
- PaperAgent World Model in the Wild: Computer-Use Agent Environment Synthesis
Agent learning is shifting from learning from human data toward learning through interaction with the world. However, scaling such learning directly in real-world compute
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.