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…
Sunday 18 October
- PaperConjugate Compilation: Self-Improving Agentic Co-Compilation for Speculative Decoding
As LLM adoption surges, scaling model serving requires unlocking stranded GPU capacity alongside deploying more GPUs. Speculative decoding brings two models into the serv
- PaperFineSplat: Fine Patches, Local Groups, Detailed Splats
Feed-forward 3D Gaussian Splatting (3DGS) promises instant scene reconstruction with high-quality novel-view synthesis. Yet, fine-grained geometry and appearance remain d
- PaperMAMath-Bench: Process-Aware and Robust Evaluation of Multimodal Multi-Agent Mathematical Reasoning
Mathematical reasoning is a fundamental capability for educational applications of Large Language Models (LLMs), where reliable problem solving requires not only correct
- PaperNo Escape from the Quadratic Barrier: Adaptive Attacks on Linear $\ell_2$ Sketches
Linear sketches estimate properties of high-dimensional inputs from a fixed low-dimensional projection. At constant accuracy, randomized Euclidean-norm sketches, notably
- PaperFix, Not Just Resample: Bounded Compiler-Guided Repair in Lean 4
Automated theorem provers often rely on sampling language models, but proof assistants like Lean reject each failed step with a precise error message --- information that
- PaperReTrace: Visual Backtracking for Efficient Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) encode images into dense visual token sequences, creating substantial attention and KV-cache overhead. Existing visual token comp
- PaperUpLoop: Upcycling Large Language Models with Gated Loop
Looped large language models trade parameter storage for recurrent computation, but most are trained from scratch. In practice, pretraining with looped depth is expensive
- PaperUtoMe: Observation-Uncertainty-Guided Token Merging for Weather Foundation Models
Weather transformers process dense reanalysis fields whose reliability varies across variables, locations, and weather regimes. Token merging can reduce computation, but
- PaperSoK: PIAtlas: Decomposing the Unbounded Prompt Injection Attack Space
Prompt injection is the dominant security risk for large-language-model (LLM) applications and agents, yet the field still lacks a coherent map of how these attacks are c
- PaperBlock Recursive Transformers for Structured Parameter Sharing
Recursive Transformers depend not only on how many parameters are shared, but also on how shared parameters are organized across depth. Existing static schemes adopt two
- PaperIndustrial Agentic AI: LLM-Driven New-Generation Agents for Smart Manufacturing
Large language models (LLMs) are enabling agents to move beyond predefined workflows toward autonomous planning and execution, creating new opportunities for smart manufa
- PaperWhen Does Better Acceptance Pay? A Controlled Study of Speculative Decoding
The throughput gains of speculative decoding depend on the trade-off between acceptance length and execution latency. We ask when additional acceptance is worth the cost
- PaperMultiAltitudeSR: Multi-Altitude Agricultural UAV Image Super-Resolution via Physical Ground Sampling Distance Conditioning
Unmanned aerial vehicles (UAVs) enable high-throughput platforms for crop monitoring but face a fundamental trade-off between flight altitude and image spatial resolution
- PaperCertified Sparse Attention via Perturbed Retrieval
Sparse attention speeds up long-context decoding by reading few keys of the KV cache, but existing methods do not control the error of a query, and on real KV caches thei
- PaperThe World as Viewed by 136 Countries: An Open, Curated, Annotated, and Multilingual Dataset of 118 Million State Media Articles
State media outlets often project their governments' narratives to target both domestic and foreign audiences. Because this content is plentiful and free to access, it ap
- PaperCorrectRTL: Boost RTL Generation Quality Through Automated Self-Correction with Instruction Decomposition
Large language models (LLMs) have shown strong promise in specification-to-RTL generation. Among the explorations, the self-correction paradigm has significantly advanced
- PaperA Measurement Perspective on Benchmarking LLM-Generated Text Detectors using Item Response Theory
Benchmarking large language model (LLM)-generated text detectors commonly relies on aggregate detector-level metrics such as accuracy, F1 score, and AUC. Although useful
- PaperRubrics Carry the Standard: Shapley Attribution for Checklist-Based LLM Judges
Checklist rubrics applied by large language model (LLM) judges have become a standard instrument for evaluating open-ended outputs and for rewarding them during training.
- PaperPRECOCIAL: Pretraining with Code Curriculums via Iterative Search for Accelerated Learning
Fully synthetic pretraining data generated by symbolic programs can bootstrap downstream training on naturalistic tasks, such as language modeling, but the generating pro
- PaperTowards Human-AI Complementarity for AI Safety
Safely overseeing AI is increasingly challenging for the humans doing it, as they must evaluate longer and more complex outputs with every new model generation. To mitiga
- PaperVisual Sufficiency Landscapes: Understanding Query-Conditioned Reliability in Visual Token Pruning
Different visual token pruning strategies retain different subsets while maintaining similar task performance. This motivates a combinatorial question: how many visual su
- PaperMeta Inverse Prompting for Video Generative Models
Recent advances in video generative models have enabled flexible conditional generation and editing pipelines, such as text-to-video, image-to-video, and reference-guided
- PaperDeGMatch: Target-Aware Reasoning Data Selection via Deconfounded Gradient Matching
Reasoning post-training on long trajectories has substantially improved the reasoning capabilities of large language models, but scaling such training to large datasets i
- PaperLabel-Space Mismatch Distorts Cross-Cohort Evaluation in Breast Cancer Molecular Subtyping
Cross-cohort evaluation of breast cancer subtype classifiers is unreliable when source and target cohorts use different annotation standards: METABRIC labels six classes,
- PaperCoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents
AI coworkers must coordinate tools, communicate across turns, and act on changing workspace state while respecting workflow constraints. Constructing training experience
- PaperRevealing what benchmark scores hide: Jointly measuring the breadth and reliability of LLM capabilities using accessibility profiles
Language model benchmarks assign each question a single outcome from one fixed wording, even though the same underlying request can be expressed in many equivalent ways.
- PaperMemPrice: Online Memory Allocation via Adaptive Pricing for Long-Horizon Agents
Long-horizon LLM agents face a fundamental allocation problem as interaction histories grow: which information to retain, how much context to devote to it, and at what gr
- PaperCasePlay: Self-Play Reinforcement Learning from Case Reports for Medical Reasoning
Reinforcement learning (RL) is a promising way to improve the clinical reasoning abilities of large language models (LLMs), but current pipelines often rely on expert-lab
- PaperControlJEPA: Principled Trajectory Regularization via Lyapunov Tube Loss
Next-token prediction leaves hidden-state trajectories largely unconstrained, while existing geometric regularizers primarily control the direction rather than the magnit
- PaperOver-Defense in Coding Agents Begins at Silent Forks
Language models behind coding agents are post-trained with outcome rewards, and recent methods concentrate credit on the turns that decide the outcome. We find that defen
- PaperRobust Direct Preference Optimization under Preference Label-Flip Attacks
Direct Preference Optimization (DPO) is widely used for offline Reinforcement Learning from Human Feedback. However, recent works have shown that DPO can be easily manipu
- PaperEpi: Towards a Persistent, Self-Improving Agent for Autonomous Research
We present Épi, an autonomous research agent that sustains investigations across model sessions and evolves its methods through accumulated experience. Épi combines persi
- PaperLowNet: Looped Wavelet Neural Networks with 24 Learnable Parameters for Solving Poisson Equations
Poisson equations frequently appear in various fields, such as mathematics, physics and informatics. Solving Poisson equation, however, is challenging. Traditional method
- PaperT-MUON: Tensorizing Muon via t-SVD for Large Language Model Pre-training
Muon has recently emerged as a strong optimizer for large language model pretraining by exploiting matrix structure through polar orthogonalization. However, it processes
- PaperMLFont: Machine Learning-Driven Font Subsetting and Range-Compact Unicode-Range Slicing for Low-Latency Web Typography
CSS3 @font-face rules with unicode-range descriptors partition web fonts into downloadable slices. While Latin fonts need ~20 KB in WOFF2, Pan-European (LGC) and East Asi
- PaperTrustAgent-RFF: Agentic Diagnostic Planning for Reliable RF Fingerprinting under Domain Shift
Radio frequency fingerprinting (RFF) models can achieve accuracy under source domain conditions but become unreliable when the receiver, distance, collection day, or envi
- PaperWhat Can't Jev Decide? Probing the Limits of One-Pass Decision Models
Jev and its open replicas choose among the options a caller supplies with a single forward pass, fast enough to decide inside an agent loop. We ask what such a model cann
- PaperMeans-Ends Analysis Helps LLMs Plan in Continuous-State Domains
LLM planning research has traditionally focused on discrete-state domains, where actions form a finite, enumerable set. Existing LLM planning frameworks largely assume ac
- PaperStable Signer V3: 4D Deformable Primitive Splatting Is All You Need for Sign Language Production
We present Stable Signer V3, an interactive high-resolution sign language avatar system built on 4D Deformable Primitive Splatting. It addresses three limitations of exis
- PaperDF-PALM: Dynamic Fusion Prompt Learning for Audio--Language Models
Few-shot audio classification requires audio--language models to distinguish variable acoustic events from limited labeled data. PALM's main formulation adapts encoded cl
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.