HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought Compression
An AI research paper on HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought 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.
Training Prompt Matters: State-Adaptive Optimization for Robust Fine-Tuning
An AI research paper on Training Prompt Matters: State-Adaptive Optimization for Robust Fine-Tuning.
Engineering 5.0 · Research 7.0 · Business 4.0
Scaling Agentic Capabilities via Grounded Interaction Synthesis
An AI research paper on Scaling Agentic Capabilities via Grounded Interaction Synthesis.
Engineering 5.0 · Research 7.0 · Business 4.0
CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning
An AI research paper on CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning.
Engineering 5.0 · Research 7.0 · Business 4.0
From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression
An AI research paper on From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression.
Engineering 5.0 · Research 7.0 · Business 4.0
Community-Aware Assessment of Social Textual Engagement and Resonance: A Human-Centric Perspective on User-Generated Content Evaluation
An AI research paper on Community-Aware Assessment of Social Textual Engagement and Resonance: A Human-Centric Perspective on User-Generated Content Evaluation.
Engineering 5.0 · Research 7.0 · Business 4.0
MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models
An AI research paper on MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models.
Engineering 5.0 · Research 7.0 · Business 4.0
Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated Rationales
An AI research paper on Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated Rationales.
Engineering 5.0 · Research 7.0 · Business 4.0
Truthful AI Advisors: A Pre-Specified Benchmark for Large Language Model Honesty Under Preference Misalignment
An AI research paper on Truthful AI Advisors: A Pre-Specified Benchmark for Large Language Model Honesty Under Preference Misalignment.
Engineering 5.0 · Research 7.0 · Business 4.0
Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs
An AI research paper on Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs.
Engineering 5.0 · Research 7.0 · Business 4.0
Citation Grounding: Detecting and Reducing LLM Citation Hallucinations via Legal Citation Graphs
An AI research paper on Citation Grounding: Detecting and Reducing LLM Citation Hallucinations via Legal Citation Graphs.
Engineering 5.0 · Research 7.0 · Business 4.0
Towards Lightweight Reliability: Using Soft Prompts for Hallucination Mitigation in Large Language Models
An AI research paper on Towards Lightweight Reliability: Using Soft Prompts for Hallucination Mitigation in Large Language Models.
Engineering 5.0 · Research 7.0 · Business 4.0
Cognitive Fatigue in Autoregressive Transformers: Formalization and Measurement
An AI research paper on Cognitive Fatigue in Autoregressive Transformers: Formalization and Measurement.
Engineering 5.0 · Research 7.0 · Business 4.0
Mellum2 Technical Report
An AI research paper on Mellum2 Technical Report.
Engineering 5.0 · Research 7.0 · Business 4.0
SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks
An AI research paper on SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks.
Engineering 5.0 · Research 7.0 · Business 4.0
Reliable Multilingual Orthopedic Decision Support from Clinical Narratives: Language-Aware Adaptation and Verification-Guided Deferral
An AI research paper on Reliable Multilingual Orthopedic Decision Support from Clinical Narratives: Language-Aware Adaptation and Verification-Guided Deferral.
Engineering 5.0 · Research 7.0 · Business 4.0
Isolating LLM Lexical Bias: A Curation-Free Triangulated Metric for Preference-Stage Learning
An AI research paper on Isolating LLM Lexical Bias: A Curation-Free Triangulated Metric for Preference-Stage Learning.
Engineering 5.0 · Research 7.0 · Business 4.0
Accommodation Goes Both Ways: Studying Linguistic Convergence Between Humans and Language Models
An AI research paper on Accommodation Goes Both Ways: Studying Linguistic Convergence Between Humans and Language Models.
Engineering 5.0 · Research 7.0 · Business 4.0
Protocol for evaluating ChatGPT in biomedical association generation and verification using a RAG-enabled, cross-model majority voting workflow
An AI research paper on Protocol for evaluating ChatGPT in biomedical association generation and verification using a RAG-enabled, cross-model majority voting workflow.
Engineering 5.0 · Research 7.0 · Business 4.0
In-Context Reward Adaptation for Robust Preference Modeling
An AI research paper on In-Context Reward Adaptation for Robust Preference Modeling.
Engineering 5.0 · Research 7.0 · Business 4.0