arXiv AI
Aug 3
Sensitivity Analysis of GRU, LSTM and Transformer Encoder in Classification of Automated Driving Systems
arXiv:2607. 28665v1 Announce Type: cross Abstract: Automated driving systems (ADSs) are becoming ubiquitous.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Aug 3
Monotone and Separable Set Functions: Characterizations and Neural Models
arXiv:2510. 23634v4 Announce Type: replace-cross Abstract: Motivated by applications for set containment problems, we consider the following fundamental problem: can we design set-to-vector functions so that the natural partial order on sets is preserved, namely $S\subseteq T \text{ if and only if } F(S)\leq F(T) $.
arXiv AI
Aug 3
Robust Bidirectional Associative Memory via Regularization Inspired by the Subspace Rotation Algorithm
arXiv:2511. 11902v2 Announce Type: replace-cross Abstract: Bidirectional Associative Memory (BAM) trained with Bidirectional Backpropagation (B-BP) often suffers from poor robustness and high sensitivity to noise and adversarial attacks.
Hugging Face Trending Papers
Aug 3
CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models
In video understanding, vision-language models (VLMs) must ingest massive numbers of visual tokens, causing the computational and memory cost of the prefill stage to rise sharply. Such visual sequences are highly redundant along the spatio-temporal dimension, yet a high compression ratio is often accompanied by the loss of critical details.
Hugging Face Trending Papers
Aug 3
Mitigating Visual Degradation in MLLMs via Spatial-Spectral Visual Anchor Learning
Despite the progress of multimodal large language models (MLLMs), they continue to exhibit deficiencies in visual perception. Following visual instruction tuning, internal MLLM representations rapidly deviate from their original semantic states during inference, causing severe information degradation.
Hugging Face Trending Papers
Aug 3
Human-LLM Alignment in Language Attitudes Toward Non-Native Japanese
Large language models (LLMs) increasingly evaluate human writing in high-stakes domains such as hiring and academic assessment, putting non-native speakers at particular risk. Drawing on the language attitudes framework, we compared human and LLM evaluations of parallel L1- and L2-written Japanese emails on three dimensions: fluency, status, and solidarity.
Hugging Face Trending Papers
Aug 3
Measuring in-context algorithmic reasoning in language models against an exact Bayes-optimal standard
Whether large language models perform genuine algorithmic reasoning or mere pattern completion is hard to test, because most benchmarks lack a ground truth for correct inductive inference. We introduce F-ICL, an in-context-learning benchmark that supplies one exactly.
Hugging Face Trending Papers
Aug 2
Scoring Rules! Statistical and Strategic Alignment for Text Evaluation Metrics
Reference-based text evaluation metrics, which are widely used to assess natural language generation systems, score a candidate response by comparing it with a reference response. The reliability of an evaluation metric is usually judged by its statistical correlation with human ratings.
Hugging Face Trending Papers
Aug 2
RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings
Generating long-form content from extensive internal reports remains challenging for organizations operating under strict privacy and security constraints, where proprietary cloud-based LLM APIs are often not viable. While locally deployed open-weight models offer a privacy-preserving alternative, existing retrieval-augmented generation (RAG) approaches on smaller models frequently lack effective global planning and accumulate factual inconsistencies over long outputs.
Hugging Face Trending Papers
Aug 2
Perspectives on Tsallis Statistics for Artificial Intelligence
Tsallis statistics generalizes Boltzmann-Gibbs statistical mechanics through a single real parameter $q$ that controls the weight assigned to rare and frequent events. Originally proposed to describe physical systems with long-range correlations, multifractal geometry, and heavy-tailed fluctuations, the framework has become a recurring ingredient in modern artificial intelligence (AI): it underlies sparse attention mechanisms (\textsc{sparsemax} and $α$-\textsc{entmax}), maximum-entropy reinforcement learning with controllable exploration, robust and heavy-tailed probabilistic models, and a family of generalized loss functions and regularizers.
Hugging Face Trending Papers
Aug 2
From Patches to Evidence Balls: Class-Conditioned Evidence Retrieval for Few-Shot Whole Slide Image Classification
Whole slide image (WSI) classification is an evidence-driven task, where diagnostic cues are often sparse, spatially organized, and class-dependent. Existing MIL and vision-language methods aggregate a large pool of patch features into a single global slide representation.
Hugging Face Trending Papers
Aug 2
VLAGuard: A Framework for Evaluating and Mitigating Physical Attention Hijacking in Vision-Language-Action Robots within Wireless Sensor Networks
Deploying Vision-Language-Action (VLA) robots as mobile edge nodes within wireless sensor networks (WSNs) requires robust protection against physical adversarial threats. We present VLAGuard, a framework to assess and mitigate a critical vulnerability: policy-critical action-to-vision attention hijacking.
Hugging Face Trending Papers
Aug 2
TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents
Large language model agents have shown strong capabilities in generating coherent and contextually appropriate responses, yet robust long-horizon dialogue remains limited by the lack of external memory that is traceable, updatable, and diagnostically transparent. Existing memory-augmented agents often store memories as isolated records or overwritable states, making it difficult to preserve how information originates, evolves, conflicts, or becomes obsolete over time.
OpenAI Blog
Jul 31
Advancing responsible AI across Europe
OpenAI shares how its safety, security, transparency, and provenance practices support responsible AI governance in Europe. The work will continue as the EU AI Act advances.
Hugging Face Trending Papers
Jul 31
Domain-Division based Progressive Learning for Source-Free Domain Adaptation
With growing privacy and portability concerns, source-free domain adaptation requires only a source pre-trained model and an unlabeled target domain, allowing for effective adaptation to the target data. Most existing self-training methods focus on selecting and exploiting samples with reliable predictions, often neglecting others.
arXiv AI
Jul 31
Contextualized Counterspeech Can Be More Persuasive Than Generic Counterspeech
arXiv:2607. 26236v1 Announce Type: cross Abstract: AI-generated counterspeech offers a scalable and effective strategy to mitigate online toxicity by promoting more constructive dialogue.
arXiv AI
Jul 31
Dual Inversion for Text-to-Image Diffusion Models: From Both Prompt and Noise Perspectives
arXiv:2607. 26735v1 Announce Type: cross Abstract: Prompt inversion, as a typical reverse engineering technique, enables text-to-image (T2I) diffusion models to generate the desired target images without extensive prompt engineering.
arXiv Machine Learning
Jul 31
Dynamically Scaled Activation Steering
arXiv:2512. 03661v2 Announce Type: replace Abstract: Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigation.
arXiv Machine Learning
Jul 31
Procedural Fairness in Multi-Agent Bandits
arXiv:2601. 10600v2 Announce Type: replace-cross Abstract: In the context of multi-agent multi-armed bandits (MA-MAB), fairness is often reduced to outcomes: maximizing welfare, reducing inequality, or balancing utilities.
arXiv AI
Jul 31
Zero-Fi: Zero-Shot Wi-Fi-Based Human Activity Recognition via Contrastive Signal-Language Alignment
arXiv:2607. 26381v1 Announce Type: cross Abstract: Wi-Fi-based human activity recognition has advanced substantially, but most existing methods assume a closed set of activities and require labeled Wi-Fi samples for every target class, limiting their ability to recognize unseen activities.