Hub / Ai Research
ai-research · WeSearch
Ai Research news.
Page 12 of Ai Research headlines on WeSearch — deduped and updated continuously from 10+ editorial sources.
ARXIV CS.AI
Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies
ARXIV CS.AI
Beyond Routing: Characterising Expert Tuning and Representation in Vision Mixture-of-Experts
ARXIV CS.AI
Lower Bounds for Advection-Diffusion Equations: An Exploration with AI-Generated Proofs
ARXIV CS.AI
Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models
ARXIV CS.AI
Retrieval-Augmented Long-Context Translation for Cultural Image Captioning: Gators submission for AmericasNLP 2026 shared task
ARXIV CS.AI
Pareto-Enhanced Portrait Generation: Vision-Aligned Text Supervision for Alignment, Realism, and Aesthetics
ARXIV CS.AI
Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs
ARXIV CS.AI
AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
ARXIV CS.AI
Design for Manufacturing: A Manufacturability Knowledge-Integrated Reinforcement Learning Framework for Free-Form Pipe Routing in Aeroengines
ARXIV CS.AI
Jointly Learning Predicates and Actions Enables Zero-Shot Skill Composition
ARXIV CS.AI
AMAR: Lightweight Attention-Based Multi-User Activity Recognition from Wi-Fi CSI
ARXIV CS.AI
REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak
ARXIV CS.AI
On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists
ARXIV CS.AI
Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting
ARXIV CS.AI
DIVE: Embedding Compression via Self-Limiting Gradient Updates
ARXIV CS.AI
Interpretable Discriminative Text Representations via Agreement and Label Disentanglement
ARXIV CS.AI
Heartbeat-Bound Hierarchical Credentials: Cryptographic Revocation for AI Agent Swarms
ARXIV CS.AI
Llamas on the Web: Memory-Efficient, Performance-Portable, and Multi-Precision LLM Inference with WebGPU
ARXIV CS.AI
Rethinking Cross-Layer Information Routing in Diffusion Transformers
ARXIV CS.AI
SCRIBE: Diagnostic Evaluation and Rich Transcription Models for Indic ASR
ARXIV CS.AI
SAVER: Selective As-Needed Vision Evidence for Multimodal Information Extraction
ARXIV CS.AI
AGPO: Adaptive Group Policy Optimization with Dual Statistical Feedback
ARXIV CS.AI
Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
ARXIV CS.AI
TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design
ARXIV CS.AI
An Application-Layer Multi-Modal Covert-Channel Reference Monitor for LLM Agent Egress
ARXIV CS.AI
Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression
ARXIV CS.AI
Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale
ARXIV CS.AI
The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering
ARXIV CS.AI
The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?
ARXIV CS.AI
PACD-Net: Pseudo-Augmented Contrastive Distillation for Glycemic Control Estimation from SMBG
ARXIV CS.AI
Correcting Stochastic Update Bias in Preconditioned Language Model Optimizers
ARXIV CS.AI
ELSA: An ELastic SNN Inference Architecture for Efficient Neuromorphic Computing
ARXIV CS.AI
Tunable MAGMAX: Preference-Aware Model Merging for Continual Learning
ARXIV CS.AI
GraphRAG on Consumer Hardware: Benchmarking Local LLMs for Healthcare EHR Schema Retrieval
ARXIV CS.AI
ArchSIBench: Benchmarking the Architectural Spatial Intelligence of Vision-Language Models
ARXIV CS.AI
USV: Towards Understanding the User-generated Short-form Videos
ARXIV CS.AI
DISC: Decoupling Instruction from State-Conditioned Control via Policy Generation
ARXIV CS.AI
Position: Let's Develop Data Probes to Fundamentally Understand How Data Affects LLM Performance
ARXIV CS.AI
Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production
ARXIV CS.AI
Evaluating the Utility of Personal Health Records in Personalized Health AI
ARXIV CS.AI
Learn-by-Wire Training Control Governance: Bounded Autonomous Training Under Stress for Stability and Efficiency
ARXIV CS.AI
AgentNLQ: A General-Purpose Agent for Natural Language to SQL
ARXIV CS.AI
KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition
ARXIV CS.AI
Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On
ARXIV CS.AI
Interference-Aware Multi-Task Unlearning
ARXIV CS.AI
Embedding by Elicitation: Dynamic Representations for Bayesian Optimization of System Prompts
ARXIV CS.AI
DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows
ARXIV CS.AI
POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents
ARXIV CS.AI
Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints
ARXIV CS.AI