EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory
An AI research paper on EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory.
Engineering 5.0 · Research 7.0 · Business 4.0
aipentium - AI Papers with Code, Datasets and Engineering Notes
aipentium: browse curated AI and robotics papers about humanoid robots, embodied AI, robot manipulation, VLA models, Diffusion Policy, Sim2Real and robot foundation models.
Numeracy in Large Language Models: Fundamental Limitations and Paths to Improvement
An AI research paper on Numeracy in Large Language Models: Fundamental Limitations and Paths to Improvement.
Engineering 5.0 · Research 7.0 · Business 4.0
LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation
An AI research paper on LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation.
Engineering 5.0 · Research 7.0 · Business 4.0
Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering
An AI research paper on Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering.
Engineering 5.0 · Research 7.0 · Business 4.0
SkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents
An AI research paper on SkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents.
Engineering 5.0 · Research 7.0 · Business 4.0
Self-Referential Induction Increases Response Instability Relative to Unresolvable and Verifiable Questions in Large Language Models
An AI research paper on Self-Referential Induction Increases Response Instability Relative to Unresolvable and Verifiable Questions in Large Language Models.
Engineering 5.0 · Research 7.0 · Business 4.0
vToken: Token-Level Virtualization for Reclaimable KV Caches
An AI research paper on vToken: Token-Level Virtualization for Reclaimable KV Caches.
Engineering 5.0 · Research 7.0 · Business 4.0
Keep, Customize, or Exit: Default Design and Token Pricing in LLM Reasoning Services
An AI research paper on Keep, Customize, or Exit: Default Design and Token Pricing in LLM Reasoning Services.
Engineering 5.0 · Research 7.0 · Business 4.0
StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems
An AI research paper on StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems.
Engineering 5.0 · Research 7.0 · Business 4.0
RAIL: An Automatic Classifier of the Artificial Intelligence Readiness Level
An AI research paper on RAIL: An Automatic Classifier of the Artificial Intelligence Readiness Level.
Engineering 5.0 · Research 7.0 · Business 4.0
UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models
An AI research paper on UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models.
Engineering 5.0 · Research 7.0 · Business 4.0
CAPRI: Contract-Aware Proof Repair for Isabelle
An AI research paper on CAPRI: Contract-Aware Proof Repair for Isabelle.
Engineering 5.0 · Research 7.0 · Business 4.0
MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification
An AI research paper on MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification.
Engineering 5.0 · Research 7.0 · Business 4.0
How AI responds to common HIV/AIDS questions: ChatGPT versus DeepSeek
An AI research paper on How AI responds to common HIV/AIDS questions: ChatGPT versus DeepSeek.
Engineering 5.0 · Research 7.0 · Business 4.0
The SrGT Proof Architecture for the Riemann Hypothesis: Where Mathematics Asks About Location and SrGT Asks About the Reason
An AI research paper on The SrGT Proof Architecture for the Riemann Hypothesis: Where Mathematics Asks About Location and SrGT Asks About the Reason.
Engineering 5.0 · Research 7.0 · Business 4.0
Large Language Models as Clinical Support Tools in Drug Information Services: Performance Comparison With Pharmacists
An AI research paper on Large Language Models as Clinical Support Tools in Drug Information Services: Performance Comparison With Pharmacists.
Engineering 5.0 · Research 7.0 · Business 4.0
APEIRON MATHEMATICS Continuous Mathematics Through Infinite-Process Representation, Stability, and Invariant Preservation
An AI research paper on APEIRON MATHEMATICS Continuous Mathematics Through Infinite-Process Representation, Stability, and Invariant Preservation.
Engineering 5.0 · Research 7.0 · Business 4.0
Toward a Gricean Retreat: Probing LLMs for Knowledge Boundaries and Referent Specificity
An AI research paper on Toward a Gricean Retreat: Probing LLMs for Knowledge Boundaries and Referent Specificity.
Engineering 5.0 · Research 7.0 · Business 4.0
DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation
An AI research paper on DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation.
Engineering 5.0 · Research 7.0 · Business 4.0
AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)
An AI research paper on AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1).
Engineering 5.0 · Research 7.0 · Business 4.0