Hugging Face Trending Papers
Jul 6
HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
We present HunyuanOCR-1. 5, a lightweight end-to-end OCR-specialized vision-language model.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
Hugging Face Trending Papers
Jul 6
LipSSD: Lipschitz-Constrained Single-Shot Detection for Adversarially Robust Object Detection
Object detectors have many applications in safety-critical systems, but they are known to be sensitive to worst-case perturbations such as adversarial attacks, which limits their applicability in real-world scenarios. Compared with classification, adversarial robustness for object detection has received less attention, and existing methods are often tied to adversarial training, whose performance may not transfer across attacks, perturbation budgets, or architectures.
Hugging Face Trending Papers
Jul 6
Non-Asymptotic Error Bounds for SMC with Biased Proposals: Application to Conditional Diffusion Sampling
Sequential Monte Carlo (SMC) methods are a natural tool for post-hoc conditioning of pretrained generative models, but in many applications the mutation kernels used by the particle system are biased approximations of an ideal Feynman--Kac flow. This paper develops a non-asymptotic error analysis for such SMC samplers.
Hugging Face Trending Papers
Jul 6
MergeSurv: Merging-Based Continual Learning for Survival Analysis on Whole-Slide Images
Survival analysis on Whole Slide Images (WSIs) is important in computational pathology for prognosis estimation and treatment planning. However, existing survival models are typically trained independently for each cancer cohort, making continual adaptation computationally expensive for gigapixel-scale WSIs.
Hugging Face Trending Papers
Jul 6
Turning Off-Policy Tokens On-Policy: A Plug-in Approach for Improving LLM Alignment
Reinforcement learning (RL) post-training for large language models (LLMs) follows a efficient paradigm of "rollout then update", which inevitably results in off-policy training data. To resolve this, Importance sampling (IS) is proposed, while the token-level ratios compound over long sequences, causing severe variance exploded.
Hugging Face Trending Papers
Jul 6
Integrated Altruistic and Fairness Preference Induces Advanced Mutual Cooperation in Sequential Social Dilemmas
Inducing cooperation among distributed agents is still a difficult problem in the field of multi-agent reinforcement learning (MARL), particularly in social dilemma situations. There, individual interests are misaligned with the common good and individual rationality leads to suboptimal group outcomes.
Hugging Face Trending Papers
Jul 6
F-ACVAE: A Federated Adaptive Conditional Variational Auto-Encoder for Privacy-Preserving Intrusion Detection in IoT Networks
The rapid proliferation of Internet of things (IoT) devices has significantly expanded the cyber-attack surface, necessitating robust and privacy-preserving intrusion detection systems (IDS). However, centralized learning approaches often suffer from severe performance degradation due to high-dimensional traffic data, extreme class imbalance, and highly non-independent and identically distributed (non-IID) data across heterogeneous edge devices.
Hugging Face Trending Papers
Jul 6
DiCE-CIR: Direct Composition Learning for Efficient Zero-Shot Composed Image Retrieval
Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image from a multimodal query consisting of a reference image and an edit text describing the desired modification. Recent ZS-CIR studies have relied on projection-based methods that map a reference image into pseudo-word tokens in the text embedding space.
Hugging Face Trending Papers
Jul 6
Machine Learning for Depression Screening and Intervention: an Original Circadian Rhythm Score-based Methodology
Depression screening from large-scale behavioral data is challenged by fragmented circadian indicators, limited interpretability, and the lack of intervention-oriented analysis. Existing approaches typically analyze sleep, activity, and social behaviors in isolation, failing to capture their joint circadian structure.
Hugging Face Trending Papers
Jul 6
Can temporal article-level credibility signals improve domain-level credibility prediction?
Web domain credibility evaluation is vital for combating misinformation. It is conducted by examining factors such as domain type, transparency, and overall reputation.
Hugging Face Trending Papers
Jul 6
EEG-SpikeAgent: Agentic Closed-Loop Program Synthesis for Automated EEG Spike Detection
Automated detection of interictal epileptiform discharges in scalp electroencephalography (EEG) is clinically important, but recent high-performing deep-learning models often trade interpretability for accuracy. We introduce EEG-SpikeAgent, a closed-loop program-synthesis framework that uses a large language model (LLM) agentic system to generate signal-processing features for spike detection in scalp EEG.
Hugging Face Trending Papers
Jul 5
Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents
Software-agent benchmarks usually report whether an agent solves a task, but the agent reaches that outcome through a harness that controls what it sees, which actions it can take, which failures are repaired, which states are verified, and which evidence is logged. We show that this harness can change the agent's multi-step beliefs even when the task, environment, and base LLM are fixed.
Hugging Face Trending Papers
Jul 5
Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems
The rapid integration of large language model-based agents into recommender systems has driven a shift from static, ranking-based pipelines toward autonomous and interactive systems that can reason, plan, and act. This survey provides a comprehensive overview of this emerging landscape by introducing a unified taxonomy grounded in the level of autonomy and three core paradigms of agentic recommender systems: agent-assisted recommendation, agent-as-recommender, and agent-as-user-simulator.
Hugging Face Trending Papers
Jul 5
AquaStereo: Enabling Underwater Stereo Matching via Depth-Conditioned Diffusion and Geometry Self-Distillation
Learning-based stereo matching models struggle in underwater environments due to scarce in-domain data and the difficulty of extracting discriminative correspondences from degraded imagery. In this work, we present $\textbf{AquaStereo}$, a perception-enhanced framework with a data simulation pipeline and a self-distillation strategy that jointly address data scarcity and feature degradation in underwater stereo matching.
Hugging Face Trending Papers
Jul 5
Agentic-V2X: Small Language Model Agents for Deadline-Aware V2X Scheduling in 5G/6G Networks
Large Language Models (LLMs) are proposed as control interfaces for next-generation networks, but their latency, hallucinations, and lack of control guarantees make them unsuitable for near-real-time packet schedulers, especially in dynamic V2X environments. This paper introduces Agentic-V2X, an architecture where a small, locally deployed language model acts as a periodic non-real-time rApp-inspired policy creator, while a lightweight xApp-like controller executes validated policies at intervals suitable for scheduling.
Hugging Face Trending Papers
Jul 5
LBR: Towards Mitigating Length Bias in Large Language Models for Recommendation
Large language models (LLMs) have recently emerged as powerful backbones for recommender systems by reformulating recommendation as a token-level generation task. Despite their promise, we identify a pervasive yet underexplored issue: $\textit{Length Bias}$.
Hugging Face Trending Papers
Jul 5
Topology-Driven Transferability Estimation for 3D Medical Vision Foundation Models
The growing number of medical vision foundation models highlights the need for effective model selection. However, mainstream selection methods rely on exhaustive fine-tuning, which is computationally expensive.
Towards Data Science
Jul 4
Stop Returning Text from RAG: The Typed Answer Contract That Prevents Hallucination
Enterprise Document Intelligence [Vol. 1 #8A] - The schema is the contract: every field is a question the pipeline asks the model, and every answer is checkable The post Stop Returning Text from RAG: The Typed Answer Contract That Prevents Hallucination appeared first on Towards Data Science .
Hugging Face Trending Papers
Jul 4
Who Gets Missed in the Tail? Thresholded Subgroup Underdiagnosis in Long-Tailed Chest X-ray Classification
In chest X-ray (CXR) classification, acceptable ranking performance can still leave rare-positive patients below threshold, especially within subgroups. We study this pre-deployment fairness problem as an audit question: after a long-tailed multi-label CXR model is converted from scores into decisions, who is missed?
Hugging Face Trending Papers
Jul 3
An Interpretable Deep Learning Framework for Discovery and Clinical Validation of Deep Radiomic Signatures in Tumor Classification
Imaging signatures are quantitative features extracted from medical images that provide clinically meaningful information for tumor diagnosis, characterization, prognosis, and treatment planning. Although deep learning has shown great potential for imaging signature discovery, its limited interpretability remains a major barrier to clinical adoption.