Search: “models”

Using the Mimi codec for metalinguistic representations

arXiv:2608.15799v1 Announce Type: new Abstract: In this paper, we focus on the dictionary of 2048 tokens used in Mimi semantic token codebook, the neural codec of the Moshi language model. We show tha

researcharxiv-cs-cl

What You Ask is What You Ground: Bridging Question Intent to Temporal Evidence for Grounded VideoQA

DGX agent

arXiv:2608.15708v1 Announce Type: new Abstract: We study a critical yet overlooked failure mode in Grounded Video Question Answering: question-invariant grounding, where models predict nearly identica

researcharxiv-cs-cv

18 Aug 2026

When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation

arXiv:2608.16515v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves large language models by grounding generation in external evidence, but it also introduces a source trus

Agents

When Is an Agent Evaluation Over? Outcome Finality and Cross-Unit Separation

arXiv:2608.14940v1 Announce Type: new Abstract: Current agent evaluations score models on the state visible at the end of a stopped run which they count as one trial. However, interpreting the score a

agentsarxiv-cs-ai

When Uncertainty Isn't Enough: An Empirical Study of Self-Correction in Code Generation

arXiv:2608.14659v1 Announce Type: new Abstract: Large language models for code generation often produce incorrect solutions without reliable indicators of failure. We study whether uncertainty estimat

Zero-MELO: Test-Time Evidence Calibration with Multimodal LLMs for Zero-Shot Micro-Gesture Recognition

arXiv:2608.14854v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) excel in general video understanding, their capability in fine-grained and motion-centric tasks remains l

AgilePE: Autonomous UAV Pursuit-Evasion via Self-Play Reinforcement Learning

arXiv:2608.14135v1 Announce Type: cross Abstract: Autonomous pursuit-evasion is a fundamental challenge for Unmanned Aerial Vehicles (UAVs), requiring rapid decision-making under tightly coupled dynam

safetyarxiv-cs-lg

AppleScab-LT: A Longitudinal Real-Field Apple Scab Dataset for Temporal Disease Progression Analysis

arXiv:2608.14235v1 Announce Type: new Abstract: The development of reliable plant disease monitoring systems is constrained by limited longitudinal datasets capturing disease progression under natural

AtomBridge: Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experiments

arXiv:2602.09430v2 Announce Type: replace-cross Abstract: Robotic laboratories play a critical role in autonomous scientific discovery by enabling scalable, continuous experimental execution. Recent v

Agents

AutoSchema: Live Schema Grounding for Agentic Text-to-Sparql over Heterogeneous Knowledge Graphs

arXiv:2608.14228v1 Announce Type: new Abstract: Life science knowledge graphs make large collections of structured data available through SPARQL, but each resource uses its own schema, identifiers, an

agentsarxiv-cs-lg

CSG-Mamba: A Convolutional Scoring Gating Vision State Space Network for Endoscopic Polyp Segmentation

arXiv:2608.14146v1 Announce Type: new Abstract: Accurate polyp segmentation is critical for computer-aided colonoscopy, yet endoscopic images often contain low-contrast boundaries, mucosal texture int

Decoding the Past: An Uncertainty-Aware Deep Learning Framework for Sex Attribution in Prehistoric Hand Stencils

arXiv:2608.14539v1 Announce Type: cross Abstract: Determining the biological sex of the individuals who created Upper Paleolithic hand stencils remains a challenging problem due to the absence of grou

Designing Sustainable Federated Learning as a Service using Neural Architecture Search

arXiv:2608.14359v1 Announce Type: new Abstract: The sustainability constraints of FLaaS consumers pose significant challenges to maintaining carbon-feasible federated training in FLaaS environments. T

applicationsarxiv-cs-ai

EchoRec: Multi-Item Prediction-Empowered Generative Recommendation via Cycle-Consistent Preference Alignment

arXiv:2608.14011v1 Announce Type: cross Abstract: Generative recommendation autoregressively generates the semantic IDs of the target item, unifying preference modeling and index retrieval within the

GhostPoint: Self-Supervised Representation Learning by Hallucinating Occluded LiDAR Structure

arXiv:2608.14428v1 Announce Type: new Abstract: 3D object detection from LiDAR point clouds is a core problem in autonomous driving. Recent advances in self-supervised learning (SSL) enable scalable p

GRPO Beyond English: A Large-Scale Study of GRPO in Non-English and Multilingual Settings

arXiv:2608.13698v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR), often optimized with Group Relative Policy Optimization (GRPO), has become a central recipe for i

safetyarxiv-cs-cl

Hybrid Quantum-inspired Kolmogorov-Arnold Networks for Privacy-Aware Federated Biosignal Learning

arXiv:2608.13914v1 Announce Type: cross Abstract: Electrocardiogram (ECG) recordings are sensitive biomedical data, limiting the ability of hospitals and wearable devices to share raw signals for cent

Join us for a fun night this Thursday (August 20th) in San Francisco! RSVP link below! 👇

Join us for a fun night this Thursday (August 20th) in San Francisco! RSVP link below! 👇 This Thursday, August 20th, we’re bringing together four leaders at the forefront of open models, coding agents

local-aiollama--x

Kolmogorov-Arnold Networks for Spatially Independent Multispectral Land Classification

arXiv:2608.13769v1 Announce Type: new Abstract: Land classification from satellite imagery is important for land management, environmental monitoring, and urban planning. Machine learning methods such

Label-Free Deep-Tissue Peripheral Nerve Detection with a Handheld Multimodal OCT Probe and NerveDetNet

arXiv:2608.13807v1 Announce Type: cross Abstract: Peripheral nerves buried beneath intact tissue are difficult to visualize during surgery and remain inaccessible to white light wide-field imaging and

Hardware

LatentAM: Real-Time, Large-Scale Latent Gaussian Attention Mapping via Online Dictionary Learning

arXiv:2602.12314v2 Announce Type: replace-cross Abstract: We present LatentAM, an online 3D Gaussian Splatting (3DGS) mapping framework that builds scalable latent feature maps from streaming RGB-D ob

hardwarearxiv-cs-cv

Learning Unsteady Aneurysm Hemodynamics with Physics-Informed DeepONets

arXiv:2608.13629v1 Announce Type: cross Abstract: Clinically actionable, patient-specific hemodynamic assessment, specifically wall shear stress, vortex structure and pressure distributions, is critic

researcharxiv-cs-lg

MINT: A Universal Zero-Shot Predictor for Transaction Data

arXiv:2608.14198v1 Announce Type: cross Abstract: Banks analyse sequential financial transaction data to perform many tasks, including fraud prevention, credit risk assessment and offer personalizatio

safetyarxiv-cs-cl

Multimarginal flow matching with optimal transport potentials

arXiv:2606.05327v2 Announce Type: replace Abstract: Flow matching (FM) has emerged as a powerful framework for learning dynamic transport maps between two empirical distributions. However, less explor

researcharxiv-cs-lg

OTIS: Learning High-Quality Time Series Features With Tiny Encoders

arXiv:2410.07299v3 Announce Type: replace-cross Abstract: We introduce OTIS, an open time series encoder that yields high-quality time series features for downstream deployment on any system, includin

applicationsarxiv-cs-ai

Participatory Moral AI Is Not Neutral: The Invisible Hand of Developers

arXiv:2608.14522v1 Announce Type: new Abstract: As AI systems make more morally loaded decisions across society, one response has been moral preference elicitation. In this approach, researchers poll

Quantum Multi-Armed Bandits and Linear Bandits: Lower Bounds and Algorithms

arXiv:2608.14319v1 Announce Type: new Abstract: We study quantum multi-armed bandits (QMAB) and quantum linear bandits (QLB) in the model of Wan et al. [2023], where the learner queries each arm or ac

safetyarxiv-cs-lg

SCVIB: Editable State-Conditioned Visual Instance Binding forMulti-Turn Personalized Localization

arXiv:2608.14148v1 Announce Type: new Abstract: We introduce editable state-conditioned visual instance binding, a multi-turn localization setting in which several support-defined instances are introd

Semantic Differentiation for Tackling Challenges in Watermarking Low-Entropy Constrained Generation Outputs

arXiv:2601.11629v2 Announce Type: replace-cross Abstract: We demonstrate that while the current approaches for language model watermarking are effective for open-ended generation, they are inadequate

researcharxiv-cs-lg

Shift Aware Transfer Learning with Adaptive Dual-Encoder Fusion for PM Forecasting in Data-Limited Environments

arXiv:2608.14456v1 Announce Type: new Abstract: Short-horizon forecasting of fine particulate matter (PM2.5) remains difficult when observations from the target domain are limited and the statistical

local-aiarxiv-cs-ai

SPARGen: Unifying Spatial Perception and Reasoning through Native Multimodal Generation

arXiv:2608.14138v1 Announce Type: cross Abstract: Spatial perception and reasoning from visual observations require recovering geometric structure, establishing correspondences, and understanding spat

The More Popular, The Harder to Forget: Adaptive Popularity for LLM Unlearning

arXiv:2608.14229v1 Announce Type: new Abstract: Popular facts are memorised more deeply during pretraining and resist removal longer than rare ones, yet existing LLM unlearning methods apply uniform g

local-aiarxiv-cs-cl

Qwen3.8-27B vs Qwen3.6-27B writing ray-tracers in BASIC

one of my llm hobbies is re-creating graphics demos i used to write in BASIC in the late 1980s. i slopped together an agentic harness and a basic-to-js transpiler in a web page i've been playing with

local-air-localllama

16 Aug 2026

Wrong! If an AI leverages symbolic operations (conditionals, operations over variables, code interpreters, etc) and neural networks it is ne…

Wrong! If an AI leverages symbolic operations (conditionals, operations over variables, code interpreters, etc) and neural networks it is neurosymbolic. If it doesn’t, it’s not. ( I laid all of this o

safetygary-marcus--x

15 Aug 2026

A Compositional Theory of Curvature in Probabilistic Circuits

arXiv:2608.12869v1 Announce Type: cross Abstract: Probabilistic Circuits (PCs) are generative models that support exact inference and, unlike deep neural networks, admit an exact and tractable measure

AmalthAI: An Open-Source Computer Vision Platform for Cultural Heritage

arXiv:2608.13343v1 Announce Type: new Abstract: Computer vision (CV) and machine learning (ML) offer new tools for cultural heritage (CH) artifact analysis, but the CV/ML pipeline remains largely inac

Attribute-Conditioned Multimodal Slot Factorization for Controllable Fashion Retrieval

arXiv:2608.12570v1 Announce Type: new Abstract: Fashion retrieval often requires satisfying multiple attributes at once, such as category, color, pattern, and demographic. Monolithic embeddings mix th

Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering

arXiv:2608.13160v1 Announce Type: cross Abstract: Multilingual retrieval-augmented generation (mRAG) equips large language models with access to globally distributed external knowledge for complex mul

Agents

Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents

arXiv:2608.12977v1 Announce Type: cross Abstract: The expanding operational capabilities of large language model (LLM) agents introduce sophisticated security threats. Runtime defenses have emerged as

agentsarxiv-cs-ai

Beyond Simulated Benchmarks: Evaluating Motion Representations for Fall Detection Under Real-World Data Scarcity

arXiv:2608.13197v1 Announce Type: new Abstract: Falls are a major health concern for older adults, and wearable sensors have been widely explored for detecting falls and enabling timely intervention.

applicationsarxiv-cs-lg

CAPRI: Contract-Aware Proof Repair for Isabelle

arXiv:2608.13459v1 Announce Type: cross Abstract: We address the use of large language models (LLMs) to help discover Isabelle proofs. An Isabelle build establishes that the submitted theory is accept

'Cause' is Mechanistic Narrative within Scientific Domains: An Ordinary Language Philosophical Critique of 'Causal Machine Learning'

arXiv:2501.05844v4 Announce Type: replace Abstract: Causal Learning has emerged as a major theme of research in statistics and machine learning in recent years, promising computational techniques to r

applicationsarxiv-cs-lg

Tutorials

Class Geometry as Supervision for Sample-Efficient Open-World Detection

arXiv:2608.12698v1 Announce Type: new Abstract: Open-world object detection requires models to recognize known categories, reject unfamiliar objects, and incorporate new classes over time. This is esp

tutorialsarxiv-cs-cv

Communication Heterogeneity and Collective Consensus in Neural Cellular Automata

arXiv:2606.21202v2 Announce Type: replace-cross Abstract: Reaching global agreement from purely local interactions is a defining problem of collective intelligence, and most models of it assume that a

Tutorials

Continual Distillation Learning for Rehearsal-Free Class-Incremental Learning via Decoupled Prompting

arXiv:2407.13911v5 Announce Type: replace Abstract: Prompt-based continual learning has shown strong performance in rehearsal-free class-incremental learning by adapting learnable prompts while freezi

tutorialsarxiv-cs-cv

DAPD: Dual-Anchored Policy Distillation

arXiv:2608.01735v2 Announce Type: replace Abstract: On-policy (self) distillation (OPSD) is increasingly adopted for language-model post-training. It strengthens the teacher with privileged informatio

Tools

Don't classify. Hallucinate!

Don't classify. Hallucinate! I still have quite a bit of older content on my blog that I never got round to tagging. My blog has 1,856 tags - likely too many to feed to an LLM in one go and say 'which

toolssimon-willison

EgoPHI: Estimating Contact and Force from Egocentric Vision

arXiv:2608.13014v1 Announce Type: new Abstract: Understanding hand-object interaction from egocentric vision is essential for modeling how people physically engage with the surrounding world. Yet reas

applicationsarxiv-cs-cv