Data Turnstile: A Scalable Open Framework for Function-Calling Data Generation
An AI research paper on Data Turnstile: A Scalable Open Framework for Function-Calling Data Generation.
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.
LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback
An AI research paper on LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback.
Engineering 5.0 · Research 7.0 · Business 4.0
DiffAttack: Evasion Attacks Against Face Recognition via Latent Diffusion Models
An AI research paper on DiffAttack: Evasion Attacks Against Face Recognition via Latent Diffusion Models.
Engineering 5.0 · Research 7.0 · Business 4.0
A Frozen Pixel-Space Diffusion Model Can Guide Itself with Its Own Samples
An AI research paper on A Frozen Pixel-Space Diffusion Model Can Guide Itself with Its Own Samples.
Engineering 5.0 · Research 7.0 · Business 4.0
MoRAE: Flow-Friendly Self-Supervised Latents for Text-to-Motion Generation
An AI research paper on MoRAE: Flow-Friendly Self-Supervised Latents for Text-to-Motion Generation.
Engineering 5.0 · Research 7.0 · Business 4.0
DualDiT: A Conditional Dual-Output Diffusion Transformer for Joint OCT Image and Segmentation Mask Generation
An AI research paper on DualDiT: A Conditional Dual-Output Diffusion Transformer for Joint OCT Image and Segmentation Mask Generation.
Engineering 5.0 · Research 7.0 · Business 4.0
MoRoute: Dynamic Routing for In-Context Multimodal Video Generation
An AI research paper on MoRoute: Dynamic Routing for In-Context Multimodal Video Generation.
Engineering 5.0 · Research 7.0 · Business 4.0
SciFigPlag-Bench: A Benchmark for Provenance-Aware Scientific Figure Plagiarism Detection
An AI research paper on SciFigPlag-Bench: A Benchmark for Provenance-Aware Scientific Figure Plagiarism Detection.
Engineering 5.0 · Research 7.0 · Business 4.0
Transcript-Managed Transformers: Monotone Multi-Agent Collapse and Universality with Two Pop-Enabled Transcripts
An AI research paper on Transcript-Managed Transformers: Monotone Multi-Agent Collapse and Universality with Two Pop-Enabled Transcripts.
Engineering 5.0 · Research 7.0 · Business 4.0
The Grokked Illusion: True Equilibrium Mitigates Catastrophic Forgetting
An AI research paper on The Grokked Illusion: True Equilibrium Mitigates Catastrophic Forgetting.
Engineering 5.0 · Research 7.0 · Business 4.0
TerraNova: A Foundation Model for the Anthropocene
An AI research paper on TerraNova: A Foundation Model for the Anthropocene.
Engineering 5.0 · Research 7.0 · Business 4.0
FairFund-Bench: Evaluating Distributive Bias in LLM Resource Allocation
An AI research paper on FairFund-Bench: Evaluating Distributive Bias in LLM Resource Allocation.
Engineering 5.0 · Research 7.0 · Business 4.0
NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observability
An AI research paper on NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observability.
Engineering 5.0 · Research 7.0 · Business 4.0
MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations
An AI research paper on MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations.
Engineering 5.0 · Research 7.0 · Business 4.0
Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates
An AI research paper on Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates.
Engineering 5.0 · Research 7.0 · Business 4.0
Scaling Scientific Discovery Environments for Turn-Level Agentic RL
An AI research paper on Scaling Scientific Discovery Environments for Turn-Level Agentic RL.
Engineering 5.0 · Research 7.0 · Business 4.0
MMShopBench: A Real-Log Benchmark for Multimodal, Multi-Turn Shopping Agents
An AI research paper on MMShopBench: A Real-Log Benchmark for Multimodal, Multi-Turn Shopping Agents.
Engineering 5.0 · Research 7.0 · Business 4.0
Benchmarking Frontier Large Language Models Against Official Crash Database Coding Using Police Crash Narratives
An AI research paper on Benchmarking Frontier Large Language Models Against Official Crash Database Coding Using Police Crash Narratives.
Engineering 5.0 · Research 7.0 · Business 4.0
Semantics of Subterfuge: Benchmarking Legal Deception Detection Against General-domain State-of-the-Art
An AI research paper on Semantics of Subterfuge: Benchmarking Legal Deception Detection Against General-domain State-of-the-Art.
Engineering 5.0 · Research 7.0 · Business 4.0
Harnessing the Wisdom of LLM Crowds through Complementarity-Driven Iterative Collaboration
An AI research paper on Harnessing the Wisdom of LLM Crowds through Complementarity-Driven Iterative Collaboration.
Engineering 5.0 · Research 7.0 · Business 4.0