EPTS: Elastic Post-Training Sparsity for Efficient Large Language Model Compression
An AI research paper on EPTS: Elastic Post-Training Sparsity for Efficient Large Language Model Compression.
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.
Improved Large Language Diffusion Models
An AI research paper on Improved Large Language Diffusion Models.
Engineering 5.0 · Research 7.0 · Business 4.0
Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing
An AI research paper on Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing.
Engineering 5.0 · Research 7.0 · Business 4.0
Agentic Knowledge Tracing: A Multi-Agent LLM Architecture for Stealth Assessment of Financial Literacy in Serious Games
An AI research paper on Agentic Knowledge Tracing: A Multi-Agent LLM Architecture for Stealth Assessment of Financial Literacy in Serious Games.
Engineering 5.0 · Research 7.0 · Business 4.0
Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis
An AI research paper on Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis.
Engineering 5.0 · Research 7.0 · Business 4.0
From Sounds to Scenes: A Benchmark for Evaluating Context-Aware Auditory Scene Understanding in Large Audio Language Models
An AI research paper on From Sounds to Scenes: A Benchmark for Evaluating Context-Aware Auditory Scene Understanding in Large Audio Language Models.
Engineering 5.0 · Research 7.0 · Business 4.0
Long-Term Simulation Exposes Cognitive-Developmental Risks in AI Companions
An AI research paper on Long-Term Simulation Exposes Cognitive-Developmental Risks in AI Companions.
Engineering 5.0 · Research 7.0 · Business 4.0
BrainAgent: A Large Language Model-Driven Multi-Agent Framework for Autonomous Brain Signal Understanding
An AI research paper on BrainAgent: A Large Language Model-Driven Multi-Agent Framework for Autonomous Brain Signal Understanding.
Engineering 5.0 · Research 7.0 · Business 4.0
CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations
An AI research paper on CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations.
Engineering 5.0 · Research 7.0 · Business 4.0
A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation
An AI research paper on A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation.
Engineering 5.0 · Research 7.0 · Business 4.0
Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models
An AI research paper on Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models.
Engineering 5.0 · Research 7.0 · Business 4.0
Cliff Tokens: Identifying Single-Token Failure Triggers in LLM Mathematical Reasoning
An AI research paper on Cliff Tokens: Identifying Single-Token Failure Triggers in LLM Mathematical Reasoning.
Engineering 5.0 · Research 7.0 · Business 4.0
STEB: A Speech-to-Speech Translation Expressiveness Benchmark for Evaluating Beyond Translation Fidelity
An AI research paper on STEB: A Speech-to-Speech Translation Expressiveness Benchmark for Evaluating Beyond Translation Fidelity.
Engineering 5.0 · Research 7.0 · Business 4.0
Evaluating LLMs on Real-World Software Performance Optimization
An AI research paper on Evaluating LLMs on Real-World Software Performance Optimization.
Engineering 5.0 · Research 7.0 · Business 4.0
SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding
An AI research paper on SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding.
Engineering 5.0 · Research 7.0 · Business 4.0
An Approach for a Supporting Multi-LLM System for Automated Certification Based on the German IT-Grundschutz
An AI research paper on An Approach for a Supporting Multi-LLM System for Automated Certification Based on the German IT-Grundschutz.
Engineering 5.0 · Research 7.0 · Business 4.0
Taxonomy of Risks on Automated Fact-Checking Systems Considering its Propagation
An AI research paper on Taxonomy of Risks on Automated Fact-Checking Systems Considering its Propagation.
Engineering 5.0 · Research 7.0 · Business 4.0
Do Encoders Suffice? A Systematic Comparison of Encoder and Decoder Safety Judges for LLM Adversarial Evaluation
An AI research paper on Do Encoders Suffice? A Systematic Comparison of Encoder and Decoder Safety Judges for LLM Adversarial Evaluation.
Engineering 5.0 · Research 7.0 · Business 4.0
MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources
An AI research paper on MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources.
Engineering 5.0 · Research 7.0 · Business 4.0
Edges Before Embeddings: A Confidence-Aware Blur Gate for Vision-Language Pipelines
An AI research paper on Edges Before Embeddings: A Confidence-Aware Blur Gate for Vision-Language Pipelines.
Engineering 5.0 · Research 7.0 · Business 4.0