arXiv AI
Jul 17
Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks
arXiv:2607. 14921v1 Announce Type: cross Abstract: Machine learning models are increasingly adapted in various domains.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
Jul 17
AgenticData: An Agentic Data Analytics System for Heterogeneous Data
arXiv:2508. 05002v2 Announce Type: replace-cross Abstract: Existing unstructured data analytics systems rely on experts to write code and manage complex analysis workflows, making them both expensive and time-consuming.
arXiv AI
Jul 17
Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models
arXiv:2607. 14552v1 Announce Type: cross Abstract: A standard recipe for distilling the reasoning ability of large language models (LLMs) is to sample chains of thought from the model, keep those that reach the correct final answer, and fine-tune on the survivors.
arXiv Machine Learning
Jul 17
Addressing Benchmarking Gaps in Large Language Models for Health and Medicine with Dynamic Red-Teaming
arXiv:2508. 00923v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to answer health-related questions and support healthcare workflows, yet evidence for their safety still relies heavily on static benchmarks that can rapidly become obsolete or be optimized against.
arXiv Machine Learning
Jul 17
On-Policy Delta Distillation
arXiv:2607. 15161v1 Announce Type: new Abstract: On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constraints imposed by reward models by providing token-level supervision from a teacher model.
arXiv AI
Jul 17
NIFA: Nonlinear IMC enhanced FPGA for efficient ML inference
arXiv:2607. 15123v1 Announce Type: cross Abstract: Recent FPGAs have improved deep learning (DL) inference efficiency through dedicated tensor blocks and in-BRAM computation.
arXiv AI
Jul 17
FindMyText: Robust, Scalable Detection of Text Containment in Large Web-Crawled Corpora
arXiv:2607. 10020v2 Announce Type: replace-cross Abstract: We present FindMyText, an open-source Python package designed to efficiently assess whether a given text appears, in part or in full, within a text corpus.
arXiv AI
Jul 17
Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learning
arXiv:2506. 12529v2 Announce Type: replace-cross Abstract: Preference-based Reinforcement Learning (PbRL) entails a variety of approaches for aligning models with human intent to alleviate the burden of reward engineering.
arXiv AI
Jul 17
LQCDMaster: Agentic Scientific Computing for Lattice Quantum Chromodynamics Research
arXiv:2607. 15001v1 Announce Type: cross Abstract: Lattice quantum chromodynamics (LQCD) provides a first-principles framework for computing hadronic observables, but its practical use remains limited by the substantial expertise required to turn research motivation into reliable computing workflows.
arXiv AI
Jul 17
Benchmarking Multimodal Large Language Models for Scientific Visualization Literacy
arXiv:2607. 15176v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly used to interpret visualizations, yet current evaluations remain largely chart-centric and provide limited evidence of understanding of scientific visualization (SciVis).
arXiv Machine Learning
Jul 17
Synthesizing real-world distributions from high-dimensional Gaussian Noise with Fully Connected Neural Network
arXiv:2604. 09091v2 Announce Type: replace Abstract: The use of synthetic data in machine learning applications and research offers many benefits, including performance improvements through data augmentation and privacy preservation of original samples.
arXiv Machine Learning
Jul 17
CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Black-Box Vision-Language Models
arXiv:2607. 14125v1 Announce Type: new Abstract: Pre-trained vision-language models (VLMs) enable zero-shot image classification by computing the similarity score between an image and textual descriptions, typically formed by inserting a class label (e.
arXiv AI
Jul 17
Asymmetric Peak-Aware Loss for Peak-Critical Time Series Forecasting
arXiv:2607. 14871v1 Announce Type: cross Abstract: In many operational time-series forecasting applications, such as crowd demand forecasting, the risk related to under-prediction is substantially higher than that of over-prediction.
arXiv AI
Jul 17
InCarEmo: A Multimodal Dataset for In-Cabin Emotion Recognition and Driver State Monitoring
arXiv:2607. 14683v1 Announce Type: new Abstract: Understanding driver emotion and state is critical for the next generation of intelligent in-cabin systems that ensure safety and enhance human-vehicle interaction.
arXiv AI
Jul 17
Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization
arXiv:2607. 14614v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) commonly uses entropy for advantage shaping.
arXiv AI
Jul 17
CoEvoT: Co-Evolving Chain-of-Thought Prompting for Graph-LLM Reasoning
arXiv:2607. 14114v1 Announce Type: cross Abstract: Graph learning under distribution shift presents a persistent challenge, where models adapt to new graphs with limited or even no supervision.
arXiv Machine Learning
Jul 17
Toward Energy-Efficient and Low-Power Arrhythmia Detection for Wearable Devices
arXiv:2607. 14747v1 Announce Type: cross Abstract: Cardiovascular diseases are the leading cause of death worldwide, and conditions such as arrhythmia often require long-term monitoring for effective detection and diagnosis.
arXiv Machine Learning
Jul 17
HyperShadow: A Benchmark for Detecting 3D Projections of Higher-Dimensional Spatial Objects
arXiv:2607. 14419v1 Announce Type: new Abstract: Machine-learning datasets labelled "4D" universally denote three spatial dimensions plus time.
arXiv AI
Jul 17
Knowing You at First Glance: Inferring Apparent Personality from Faces
arXiv:2607. 14631v1 Announce Type: cross Abstract: Inferring apparent personality from facial images is important in social scenarios for embodied agents in human-robot interaction.
arXiv AI
Jul 17
When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space
arXiv:2607. 15218v1 Announce Type: new Abstract: Large language models (LLMs) increasingly serve as high-level planners for embodied agents, where linguistically benign instructions can become unsafe once grounded in the physical world.