Multi-Reward GRPO Fine-Tuning for De-biasing Large Language Models: A Study Based on Chinese-Context Discrimination Data
arxiv.org·3d
🧠AI
Flag this post
DPRM: A Dual Implicit Process Reward Model in Multi-Hop Question Answering
arxiv.org·2d
🧠AI
Flag this post
Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models
arxiv.org·3d
🧠AI
Flag this post
Production-Ready AI Agents: 8 Patterns That Actually Work (with Real Examples from Bank of America…
pub.towardsai.net·20h
🧠AI
Flag this post
Radiology Workflow-Guided Hierarchical Reinforcement Fine-Tuning for Medical Report Generation
arxiv.org·4h
🧠AI
Flag this post
Wasm: A Pipeline for Constructing Structured Arabic Interleaved Multimodal Corpora
arxiv.org·3d
🧠AI
Flag this post
An Efficient Gradient-Aware Error-Bounded Lossy Compressor for Federated Learning
arxiv.org·3d
⚡real-time analytics
Flag this post
Bridging Accuracy and Explainability in EEG-based Graph Attention Network for Depression Detection
arxiv.org·3d
🧠AI
Flag this post
I made open-source version of iLoveImg
🦀Rust
Flag this post
A transfer condition-focused model for battery capacity forecast
sciencedirect.com·1d
🧠AI
Flag this post
Personality over Precision: Exploring the Influence of Human-Likeness on ChatGPT Use for Search
arxiv.org·3d
🧠AI
Flag this post
LLMs vs. Traditional Sentiment Tools in Psychology: An Evaluation on Belgian-Dutch Narratives
arxiv.org·2d
🧠AI
Flag this post
Relation as a Prior: A Novel Paradigm for LLM-based Document-level Relation Extraction
arxiv.org·2d
🧠AI
Flag this post
Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training
arxiv.org·3d
🧠AI
Flag this post
A novel hybrid model for state of health prediction in lithium batteries based on non-stationary transformers optimized by tree-structured Parzen estimator cons...
sciencedirect.com·1d
⚡real-time analytics
Flag this post
AdaCuRL: Adaptive Curriculum Reinforcement Learning with Invalid Sample Mitigation and Historical Revisiting
arxiv.org·1d
🧠AI
Flag this post
Baidu unveils proprietary ERNIE 5 beating GPT-5 performance on charts, document understanding and more
venturebeat.com·12h
⚡real-time analytics
Flag this post
Knowledge Graph Analysis of Legal Understanding and Violations in LLMs
arxiv.org·1d
🧠AI
Flag this post
Loading...Loading more...