arXiv AI
Aug 13
Agent Skills Can Be Harmful: An Empirical Study of Skill-Induced Failures in LLM Agents
arXiv:2608. 11888v1 Announce Type: new Abstract: Agent skills are the de facto mechanism for extending LLM agents with reusable guidance.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
Hugging Face Trending Papers
Aug 13
SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention
Diffusion Transformers (DiTs) incur quadratic self-attention cost over spatiotemporal tokens. Existing training-free sparse attention methods often construct sparse masks from block-level or cluster-level proxy scores, which can obscure fine-grained differences among keys and miss high contribution keys under aggressive sparsity.
Hugging Face Trending Papers
Aug 13
CRAFT: LLM-Based Iterative Refinement for Temporal Reasoning over Clinical Narratives
Understanding the temporal progression of symptoms in clinical narratives is critical for disease monitoring, safety surveillance, and causality assessment. Clinical narratives, however, rarely provide explicit temporal anchors.
Hugging Face Trending Papers
Aug 13
ViTOED: A Dataset for Target-Oriented Emotion Detection on Vietnamese Social Media Texts
This paper introduces ViTOED, a novel dataset for target-oriented emotion detection in Vietnamese social media texts. The ViTOED comprises 10,985 user comments and 21,244 manually annotated opinion quadruples (source, target, expression, polarity) that follow strict guidelines.
Hugging Face Trending Papers
Aug 13
Dual-Stream Cross-Anchor Correction Grounding Long-Form Captions and the Domain Limits of Object-Level Anchors
Object hallucination in multimodal large language models arises when language priors and corpus co-occurrence bias outweigh the visual evidence, with nothing tying an individual object mention to what the image shows. Most remedies intervene at decoding time without training, yet under a unified protocol their benefit is confined to short captions;supervised fine-tuning (SFT) on a detail- rich corpus lengthens captions, but over forty percent still name absent objects.
Hugging Face Trending Papers
Aug 13
A Cloud-Edge System for Multimodal Clinical Screening in Resource-Constrained Rural Settings
Medical AI has demonstrated specialist-level diagnostic accuracy, yet these capabilities remain largely inaccessible in resource-constrained rural settings where bandwidth is scarce, compute is limited, and clinical decision-making requires integrating heterogeneous modalities. We introduce a cloud--edge collaborative architecture that addresses these constraints: lightweight, domain-specific models on the edge transform raw medical data into compact structured outputs, while a cloud LLM synthesizes these outputs into clinical summaries.
Hugging Face Trending Papers
Aug 13
Error-Aware Reverse Auction Mechanism for Large Language Model Routing
Routing each query to a cost-effective large language model (LLM) is critical for balancing quality and cost, yet most routers rely on a centralized task center to predict model performance, creating an information-risk mismatch and a scalability bottleneck as the model pool grows. We propose a market-based routing paradigm that shifts ex-ante prediction to LLM providers via a reverse auction, where providers bid with self-predicted success probabilities and execution costs.
Simon Willison
Aug 12
DeepSeek V4 Pro 0813 (on OpenRouter)
DeepSeek V4 Pro 0813 (on OpenRouter) The latest DeepSeek Pro model is now available, via API only. I had to link to OpenRouter because DeepSeek don't have any obvious announcement page for their new model.
Simon Willison
Aug 12
alchemy-utils 0.1a0
Release: alchemy-utils 0. 1a0 I've long pondered what a database agnostic version of my sqlite-utils Python library and CLI utility might look like.
Hugging Face Trending Papers
Aug 12
Can Vision-Language Models Assess Proxemic Risk from Egocentric Robot Images?
Assessing proxemic danger from a robot's egocentric perspective is critical for safe embodied navigation in human environments and requires both visual and contextual reasoning. We evaluate three opensource vision-language models (VLMs) (\textit{InternVL}, \textit{Qwen-VL}, and \textit{SmolVLM}) on the classification of egocentric robot images into four danger levels, comparing three prompting strategies and two rounds of QLoRA fine-tuning against a stratified random baseline.
Hugging Face Trending Papers
Aug 12
Constructing Dynamic Master Logic Models as Knowledge Graphs for Complex System Diagnostics Using Retrieval-Augmented Large Language Models
Dynamic Master Logic (DML) provides a hierarchical framework for representing system behavior by linking functional objectives to underlying structural elements. However, DML construction typically relies on expert interpretation of technical documentation, limiting scalability for complex systems.
Hugging Face Trending Papers
Aug 12
Beyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence
Modern black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation, yet their lack of fine-grained control and reliability presents significant challenges in professional workflows. Their inherent stochasticity causes minor variations in textual prompts or hyperparameters to yield drastically different outputs often necessitating inefficient, brute-force trial-and-error processes.
Hugging Face Trending Papers
Aug 12
Domain-Aware Lightweight Spectral-Grouped Convolutions for Hyperspectral Fish Freshness Classification
Hyperspectral imaging (HSI) offers nondestructive assessment of fish freshness by detecting biochemical alterations across spectral bands. However, conventional deep learning approaches do not fully address the particular characteristics of HSI data, such as spectral dominance over spatial textures, ordinal label structure, and a small number of training samples.
Hugging Face Trending Papers
Aug 12
SCOUT: Unlocking Enhanced Spatial Reasoning via Structured Chain-of-Thought and Multi-Objective Process Reward
Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning. Recent reinforcement learning (RL) methods aim to close this gap with verifiable outcomes, yet they suffer from poor credit assignment across intermediate reasoning steps.
Hugging Face Trending Papers
Aug 12
SemPlan: Benchmarking Structured Semantic Planning for LLM-Based Queries over Enterprise Data
Natural-language interfaces to enterprise data must translate underspecified requests into governed, executable behavior while controlling invalid queries, policy failures, cost, and nondeterminism. SemPlan Benchmark evaluates this architectural design space with a deterministic synthetic bilingual benchmark containing 1,800 cases in English and Brazilian Portuguese; 1,200 cases form the frozen scientific evaluation subset.
Hugging Face Trending Papers
Aug 12
Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus
We present the first systematic study of Massive activations (MAs) in layer-interleaved HLA LLMs and uncover two architecture-aligned morphologies: MAs consistently spike immediately before full attention layers, forming pre-attention spikes (PAS), and can persist through intervening linear attention layers, giving rise to inter-spike plateaus (ISP). As full attention becomes denser, successive PAS become increasingly connected through ISP, ultimately recovering the stable MA morphology of full attention LLMs.
Simon Willison
Aug 12
Quoting Florian Herrengt
But then users start to report a weird bug. It's the 4th time your team has been trying to fix it.
Hugging Face Trending Papers
Aug 12
Task- and dataset-specific information in protein language models
Protein language models (PLMs) have transferred the latest advances from natural language processing to computational biology. These models, trained on large corpora of protein sequence data, are widely used to translate amino acid sequences into latent-space embeddings, ready for use in diverse downstream tasks (DTs).
Towards Data Science
Aug 12
Building Multimodal Workflows with a Local LLM
Image inputs and structured outputs with Gemma 4 and Ollama The post Building Multimodal Workflows with a Local LLM appeared first on Towards Data Science .
Hugging Face Trending Papers
Aug 12
Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed
Small Language Models (SLMs) have emerged as a more efficient alternative to traditional Large Language Models (LLMs), offering promising potential in resource-constrained scenarios. Existing approaches to building SLMs typically follow two paths: training compact models from scratch, or compressing larger pre-trained models using methods such as pruning, quantization, or distillation.