The AI Wire

146 articles tagged "cs-AI" — page 4 of 5

DiffusionBrowser: Interactive Diffusion Previews via Multi-Branch Decoders (arxiv.org)

2025-12-16|paper|arXiv

<think>

cs-CV cs-AI cs-GR

Causal Inference in Energy Demand Prediction [TOP LAB](arxiv.org)

2025-12-15|paper|arXiv

<think>

Atomic Action Slicing: Planner-Aligned Options for Generalist VLA Agents [TOP LAB](arxiv.org)

2025-12-15|paper|arXiv

<think>

cs-LG cs-AI cs-RO

Any4D: Unified Feed-Forward Metric 4D Reconstruction [TOP LAB](arxiv.org)

2025-12-14|paper|arXiv

<think>

cs-CV cs-AI cs-LG

Textual Data Bias Detection and Mitigation - An Extensible Pipeline with Experimental Evaluation [TOP LAB](arxiv.org)

2025-12-14|paper|arXiv

<think>

Any4D: Unified Feed-Forward Metric 4D Reconstruction [TOP LAB](arxiv.org)

2025-12-13|paper|arXiv

<think>

cs-CV cs-AI cs-LG

Textual Data Bias Detection and Mitigation - An Extensible Pipeline with Experimental Evaluation [TOP LAB](arxiv.org)

2025-12-13|paper|arXiv

<think>

Any4D: Unified Feed-Forward Metric 4D Reconstruction [TOP LAB](arxiv.org)

2025-12-12|paper|arXiv

<think>

cs-CV cs-AI cs-LG

Textual Data Bias Detection and Mitigation - An Extensible Pipeline with Experimental Evaluation [TOP LAB](arxiv.org)

2025-12-12|paper|arXiv

<think>

Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing [TOP LAB](arxiv.org)

2025-12-11|paper|arXiv

<think>

cs-AI cs-CR cs-CY

Analyzing Planner Design Trade-offs for MAPF under Realistic Simulation [TOP LAB](arxiv.org)

2025-12-11|paper|arXiv

<think>

Hands-on Evaluation of Visual Transformers for Object Recognition and Detection [TOP LAB](arxiv.org)

2025-12-11|paper|arXiv

<think>

Astra: General Interactive World Model with Autoregressive Denoising (arxiv.org)

2025-12-10|paper|arXiv

<think>

cs-CV cs-AI cs-LG

Revisiting the Scaling Properties of Downstream Metrics in Large Language Model Training [TOP LAB](arxiv.org)

2025-12-10|paper|arXiv

<think>

cs-LG cs-AI cs-CL

CARLoS: Retrieval via Concise Assessment Representation of LoRAs at Scale [TOP LAB](arxiv.org)

2025-12-10|paper|arXiv

<think>

WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling [TOP LAB](arxiv.org)

2025-12-09|paper|arXiv

<think>

ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning [TOP LAB](arxiv.org)

2025-12-09|paper|arXiv

<think>

cs-AI cs-CL cs-LG

Enhancing Retrieval-Augmented Generation with Entity Linking for Educational Platforms (arxiv.org)

2025-12-08|paper|arXiv

<think>

cs-IR cs-AI cs-CL

Trusted AI Agents in the Cloud [TOP LAB](arxiv.org)

2025-12-08|paper|arXiv

<think>

cs-CR cs-AI cs-MA

Training-Time Action Conditioning for Efficient Real-Time Chunking (arxiv.org)

2025-12-08|paper|arXiv

<think>

The Universal Weight Subspace Hypothesis (arxiv.org)

2025-12-07|paper|arXiv

<think>

cs-LG cs-AI cs-CV

Semantic Soft Bootstrapping: Long Context Reasoning in LLMs without Reinforcement Learning [TOP LAB](arxiv.org)

2025-12-07|paper|arXiv

<think>

cs-CL cs-AI cs-IT

The Universal Weight Subspace Hypothesis (arxiv.org)

2025-12-06|paper|arXiv

<think>

cs-LG cs-AI cs-CV

Semantic Soft Bootstrapping: Long Context Reasoning in LLMs without Reinforcement Learning [TOP LAB](arxiv.org)

2025-12-06|paper|arXiv

<think>

cs-CL cs-AI cs-IT

Autonomous Reinforcement Learning Robot Control with Intel's Loihi 2 Neuromorphic Hardware [TOP LAB](arxiv.org)

2025-12-04|paper|arXiv

<think>

cs-RO cs-AI cs-LG

EfficientFlow: Efficient Equivariant Flow Policy Learning for Embodied AI (arxiv.org)

2025-12-02|paper|arXiv

<think>

cs-RO cs-AI cs-CV

A Diffusion Model Framework for Maximum Entropy Reinforcement Learning (arxiv.org)

2025-12-02|paper|arXiv

<think>

cs-LG cs-AI stat-ML

GrndCtrl: Grounding World Models via Self-Supervised Reward Alignment [TOP LAB](arxiv.org)

2025-12-02|paper|arXiv

<think>

cs-CV cs-AI cs-LG

Exploring Human Perceptions of AI Responses: Insights from a Mixed-Methods Study on Risk Mitigation in Generative Models [TOP LAB](arxiv.org)

2025-12-02|paper|arXiv

<think>

cs-CL cs-AI cs-HC

Revisiting Generalization Across Difficulty Levels: It's Not So Easy (arxiv.org)

2025-11-29|paper|arXiv

We investigate how well large language models (LLMs) generalize across different task difficulties, a key question for effective data curation and evaluation. Existing research is mixed regarding whet...

← Prev4 / 5Next →