Towards Data Science
Jul 16
How to Get the Most Out of Claude Fable 5
Maximize your Claude Fable 5 usage The post How to Get the Most Out of Claude Fable 5 appeared first on Towards Data Science .
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
Jul 16
Benchmarking Face Recognition without Real Faces
Synthetic face datasets have become effective enough to train face recognition models with accuracy rivaling that of models trained on real photographs. This progress sidesteps the ethical and legal burdens of collecting real biometric data, yet evaluation has not kept pace.
Hugging Face Trending Papers
Jul 16
Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality
Large Language Models (LLMs) perform differently on identical programming tasks when prompted in different natural languages, a phenomenon known as language bias. While this behavior has been widely studied for general text generation, its impact on code generation quality and programming conventions remains largely unexplored.
Hugging Face Trending Papers
Jul 16
An LLM-Based Automatic Sportscast Solution for Robot Soccer Matches
RoboCup has always been a scenario to develop systems that solve real-world problems. Driven by the main goal of playing against the 2050 FIFA World Cup champions, the RoboCup Soccer leagues need to constantly measure how the research community is progressing.
Hugging Face Trending Papers
Jul 16
ExaGEMM: Exploration Framework for CPU-Driven ML Inference via Associative In-Register Computing for Low-Bit GEMM
Low-bit GEMM is increasingly central to efficient ML inference, yet very-low-bit execution remains a poor fit for conventional CPUs. Practical deployment spans fragmented regimes-from 1/2/4-bit weights to varying activation precision-whose feasibility, reuse opportunity, and support cost differ under fixed SIMD and register-file budgets, making lightweight CPU support selection a first-class design problem.
arXiv AI
Jul 16
LAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning
arXiv:2607. 13501v1 Announce Type: new Abstract: Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions.
arXiv AI
Jul 16
When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation
arXiv:2605. 24902v2 Announce Type: replace-cross Abstract: Reasoning-enabled LLMs perform strongly on medical reasoning benchmarks, but it remains unclear whether these gains transfer to structured clinical documentation; we investigate this question using SOAP note generation from clinical dialogue in a source-aware benchmark spanning OMI Health, ACI-Bench, and PriMock57.
arXiv AI
Jul 16
The Refusal Residue: When Probes Catch Alignment Faking and When They Don't
arXiv:2607. 13346v1 Announce Type: cross Abstract: Alignment faking is dangerous because a model can appear compliant under monitoring while preserving behavior it would reveal when unmonitored.
arXiv AI
Jul 16
AIMO Interpretability Challenge
arXiv:2607. 13899v1 Announce Type: new Abstract: We propose the AIMO Interpretability Challenge, a competition on distinguishing robust from spurious reasoning in frontier mathematical language models based on the models' internal mechanisms.
arXiv AI
Jul 16
Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth
arXiv:2607. 14018v1 Announce Type: cross Abstract: We investigate how each component of the Transformer feedforward block architecture design determines how much rank survives across depth at initialization.
arXiv AI
Jul 16
Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation
arXiv:2607. 13125v1 Announce Type: cross Abstract: We introduce Boogu-Image-0.
arXiv AI
Jul 16
Cost-Optimal Foundation Model Deployment Portfolio for Transportation Management
arXiv:2607. 13239v1 Announce Type: new Abstract: Foundation models, including large language models (LLMs) and vision-language models (VLMs), are increasingly used for transportation management center (TMC) tasks such as anomaly detection, incident reporting, and traveler information.
arXiv AI
Jul 16
Anatomically Faithful but Temporally Blind: Auditing Attribution for Left-Ventricular Ejection-Fraction Estimation from Echocardiography
arXiv:2607. 13738v1 Announce Type: cross Abstract: Background and Objective: Deep video models estimate left-ventricular ejection fraction (EF) from echocardiography with near-expert accuracy, and post-hoc attribution (Chefer relevance for transformers, Grad-CAM for CNNs) is increasingly used to certify that models "look at the right place.
arXiv AI
Jul 16
Adversarial Prompting Framework for AI Safety Assessment
arXiv:2607. 13453v1 Announce Type: cross Abstract: Artificial Intelligence (AI), especially Generative AI (GenAI), adoption has increased in industries significantly in recent years.
arXiv AI
Jul 16
RADAR: Closed-Loop Robotic Data Generation via Semantic Planning and Autonomous Causal Environment Reset
arXiv:2603. 11811v2 Announce Type: replace-cross Abstract: The acquisition of large-scale physical interaction data, a critical prerequisite for modern robot learning, is severely bottlenecked by the prohibitive cost and scalability limits of human-in-the-loop collection paradigms.
arXiv AI
Jul 16
Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild
arXiv:2607. 13881v1 Announce Type: cross Abstract: Human-object interaction detection (HOID) has traditionally been formulated as a supervised detection problem over predefined interaction categories.
arXiv Machine Learning
Jul 16
Precomputing the Future-Offset Average in TriAttention
arXiv:2607. 13051v1 Announce Type: cross Abstract: TriAttention is a recent method for shrinking the KV cache of long-reasoning LLMs: it scores each cached key by how much attention it is likely to receive and evicts the lowest-scoring ones.
arXiv Machine Learning
Jul 16
Securing LLMs in the Wild: Privacy and Security Challenges at the Edge
arXiv:2607. 13088v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly moving from research settings into the wild, deployed on enterprise infrastructure, personal devices, and edge platforms.
arXiv AI
Jul 16
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
arXiv:2510. 11686v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model.
arXiv AI
Jul 16
OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3
arXiv:2607. 01531v2 Announce Type: replace Abstract: Learning how an environment behaves from interaction is central to building agents that adapt to unfamiliar tasks.