arXiv AI
Aug 10
BONSAI: Evolvability-Guided Tree Search over Skills
arXiv:2608.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
Aug 10
StepJack: Benchmarking Computer-Use Agent Safety Against Multi-Step Indirect Prompt Injection
arXiv:2608. 06477v1 Announce Type: cross Abstract: Computer-use agents (CUAs) face a growing threat from indirect prompt injection, where adversarial instructions are planted in the environment such as web pages.
arXiv AI
Aug 10
Cluster Attention for Graph Machine Learning
arXiv:2604. 07492v2 Announce Type: replace-cross Abstract: Message Passing Neural Networks have recently become the most popular approach to graph machine learning tasks; however, their receptive field is limited by the number of message passing layers.
arXiv AI
Aug 10
Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination
arXiv:2608. 07341v1 Announce Type: cross Abstract: Test data from public benchmarks inevitably leaks into pretraining corpora, inflating evaluation scores once memorized.
arXiv AI
Aug 10
Density-aware Hierarchical Clustering Based on Element-Categorized Connection Subgraphs
arXiv:2608. 06990v1 Announce Type: cross Abstract: Clustering is a fundamental data mining technique for pattern recognition through unsupervised learning.
arXiv Machine Learning
Aug 10
Tensor Network Kernel Machines: A JAX Framework for Machine Learning and Nonlinear System Identification
arXiv:2608. 07043v1 Announce Type: cross Abstract: Developing nonlinear models that are both expressive and computationally efficient remains a challenge in machine learning and nonlinear system identification.
arXiv AI
Aug 10
Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination
arXiv:2608. 07302v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) often suffer from object hallucination, generating objects that are absent from the image.
arXiv AI
Aug 10
Interpretable reinforcement learning with decision-tree pruning
arXiv:2608. 07151v1 Announce Type: cross Abstract: Reinforcement learning policies are difficult to inspect, but interpreting them is a prerequisite for trustworthiness.
arXiv AI
Aug 10
Geo-Spatial Concept Probing of Large Language Models: Abstraction, Compositionality, and Grounding
arXiv:2608. 07353v1 Announce Type: cross Abstract: Understanding concepts is fundamental to generalization.
arXiv Machine Learning
Aug 10
Graph Machine: Exploring Edge Mechanisms as an Inductive Bias
arXiv:2608. 06834v1 Announce Type: new Abstract: Transformers provide a powerful architecture for global content-based matching, but reasoning problems may benefit from a stronger inductive bias toward iterative traversal of latent relations.
Hugging Face Trending Papers
Aug 10
GeoUniPR: A Geometry-Consistent Unified Framework for Cross-Modal Place Recognition
Cross-modal place recognition (CMPR) aims to identify the same location across heterogeneous sensing modalities, such as vision and LiDAR. Existing methods commonly bridge the modality gap using complex alignment modules, multi-stage training, or full fine-tuning of pretrained backbones.
Hugging Face Trending Papers
Aug 10
SI-Edit: Toward Sketch-Instruction Guided Local Image Editing with Pixel-Level Precision
Despite rapid advances in generative models, achieving pixel-level precision in sketch-based image editing remains a persistent challenge, particularly for fine-grained local deformations. This gap stems primarily from the critical shortage of high-quality, publicly available benchmark datasets that jointly provide geometric constraints and semantic instructions.
Hugging Face Trending Papers
Aug 10
Evo-Bench: Can Language Models Improve Agent Harness?
Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emerging frontier is harness evolution---the agent's capacity to autonomously optimize its own operating harness.
Hugging Face Trending Papers
Aug 10
Diagnosing as Cardiologists Do: ECG Agents with Doctor-Grounded Priors for Clinical Reasoning Across Diseases and Populations
Cardiologists interpret electrocardiograms by localizing waveform components, measuring rhythm and interval patterns, and translating these structured observations into diagnostic evidence. Whether this expert reading process can serve as an effective prior for ECG agents remains unclear.
Hugging Face Trending Papers
Aug 10
Measuring the Tokenization Premium: A Cost Audit for Underserved Language Communities
Large language models are increasingly deployed as general-purpose educational and technical assistance systems, but their underlying infrastructure does not treat languages equally. One underexamined source of disparity is tokenization: semantically equivalent content can require substantially different token counts across languages, affecting API cost, latency, and usable context length before a model is invoked.
Hugging Face Trending Papers
Aug 10
Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization
Users of modern platforms repeatedly need summaries of recent dialogue, but the window rarely contains enough context to be interpreted on its own. We formalize this setting as streaming dialogue summarization, where a system must summarize a current window using selective memory from an unbounded history under a fixed budget.
Hugging Face Trending Papers
Aug 9
Gradient Under Microscope: Benchmarking Resource Utilization of Memory-Efficient Gradient Computation Methods
AI training's rising resource intensity is straining electricity supplies and carbon budgets, motivating systematic study of memory-efficient training on constrained hardware. We benchmark five gradient optimizers (SGD, Adam, Adagrad, Adadelta, and Conjugate Gradient Descent) under three memory strategies (standard training, gradient checkpointing, and gradient accumulation) across four transformer architectures (ViT, ModernBERT, Llama 3.
Hugging Face Trending Papers
Aug 9
Improving Generalization Robustness of Multimodal RLVR
Reinforcement Learning with Verifiable Rewards (RLVR) makes Multimodal Large Language Models more accurate, but the gains are brittle: simply paraphrasing a question or changing the prompt template can degrade them, which challenges reliable deployment in high-stakes scenarios like medical VQA. We trace this to two issues of the standard RL objective.
Hugging Face Trending Papers
Aug 9
OmnilingualGAIA2: Evaluating the Multilingual Gap in Frontier AI Agents
Agentic benchmarks aim to measure how well AI agents plan, search, execute, and recover within realistic multi-tool environments, but they are almost exclusively in English. As AI agents are globally deployed to a linguistically diverse user base, whether agentic competence measured in English transfers to other languages remains an open question.
Hugging Face Trending Papers
Aug 9
TomaMMU: A Comprehensive Multimodal Understanding Benchmark for Tomato Leaf Diseases
To address this gap, we introduce TomaMMU, a large-scale Tomato leaf disease MultiModal Understanding dataset, alongside TomaBench, a benchmark for evaluating VLMs on tomato disease understanding. TomaMMU comprises 28,808 high-quality images spanning 15 categories and 213,119 human-annotated visual question-answer pairs, generated through a three-stage pipeline comprising Data Collection, Human Annotation, and Question-Answer Generation.