Hub / Ai Research
ai-research · WeSearch
Ai Research news.
Page 10 of Ai Research headlines on WeSearch — deduped and updated continuously from 10+ editorial sources.
ARXIV CS.AI
Teaching AI Through Benchmark Construction: QuestBench as a Course-Based Practice for Accountable Knowledge Work
ARXIV CS.AI
PALS: Power-Aware LLM Serving for Mixture-of-Experts Models
ARXIV CS.AI
Mind the Sim-to-Real Gap & Think Like a Scientist
ARXIV CS.AI
AiraXiv: An AI-Driven Open-Access Platform for Human and AI Scientists
ARXIV CS.AI
DeepWeb-Bench: A Deep Research Benchmark Demanding Massive Cross-Source Evidence and Long-Horizon Derivation
ARXIV CS.AI
Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning
ARXIV CS.AI
Neural Estimation of Pairwise Mutual Information in Masked Discrete Sequence Models
ARXIV CS.AI
GraphDiffMed: Knowledge-Constrained Differential Attention with Pharmacological Graph Priors for Medication Recommendation
ARXIV CS.AI
Improving Quantized Model Performance in Qualitative Analysis with Multi-Pass Prompt Verification
ARXIV CS.AI
Parallel LLM Reasoning for Bias-Resilient, Robust Conceptual Abstraction
ARXIV CS.AI
Pseudo-Siamese Network for Planning in Target-Oriented Proactive Dialogues
ARXIV CS.AI
Data Scaling as Progressive Coverage of a Predictive Contribution Spectrum
ARXIV CS.AI
FlowLM: Few-Step Language Modeling via Diffusion-to-Flow Adaptation
ARXIV CS.AI
Evaluating multimodal emotion recognition in proactive conversational agents: A user study
ARXIV CS.AI
Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning
ARXIV CS.AI
Under Pressure: Emotional Framing Induces Measurable Behavioral Shifts and Structured Internal Geometry in Small Language Models
ARXIV CS.AI
GrandGuard: Taxonomy, Benchmark, and Safeguards for Elderly-Chatbot Interaction Safety
ARXIV CS.AI
RealUserSim: Bridging the Reality Gap in Agent Benchmarking via Grounded User Simulation
ARXIV CS.AI
PrivacyAkinator: Articulating Key Privacy Design Decisions by Answering LLM-Generated Multiple-choice Questions
ARXIV CS.AI
Governance by Design: Architecting Agentic AI for Organizational Learning and Scalable Autonomy
ARXIV CS.AI
Leveraging Vision-Language Models to Detect Attention in Educational Videos
ARXIV CS.AI
Network-Based Interventions for HIV Prevention via Cascade-Aware Suppression of Transmission
ARXIV CS.AI
AI-Assisted Competency Assessment from Egocentric Video in Simulation-Based Nursing Education
ARXIV CS.AI
TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data
ARXIV CS.AI
Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine
ARXIV CS.AI
Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry
ARXIV CS.AI
LEAP: A closed-loop framework for perovskite precursor additive discovery
ARXIV CS.AI
Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search
ARXIV CS.AI
GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents
ARXIV CS.AI
CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning
ARXIV CS.AI
Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization
ARXIV CS.AI
ProcBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents
ARXIV CS.AI
Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting
ARXIV CS.AI
Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty
ARXIV CS.AI
FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning
ARXIV CS.AI
Instance Discrimination for Link Prediction
ARXIV CS.AI
It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
ARXIV CS.AI
Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing
ARXIV CS.AI
Generation of Heterogeneous PET Images from Uniform Organ Activity Maps Using a Pretrained Domain-Adapted Diffusion Model
ARXIV CS.AI
Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding
ARXIV CS.AI
Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity
ARXIV CS.AI
Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs
ARXIV CS.AI
Smaller Abstract State Spaces Enable Cross-Scale Generalization in Reinforcement Learning
ARXIV CS.AI
Modality-Decoupled Online Recursive Editing
ARXIV CS.AI
PolycubeNet: A Dual-latent Diffusion Model for Polycube-Based Hexahedral Mesh Generation
ARXIV CS.AI
You Don't Need Attention: Gated Convolutional Modeling for Watch-Based Fall Detection
ARXIV CS.AI
Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis
ARXIV CS.AI
ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison
ARXIV CS.AI
Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning
ARXIV CS.AI