Awesome AI for Science
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Bhavya Kailkhura — most-cited papers & profile · AI for Science
← authors
·
overview
Bhavya Kailkhura
15
papers ·
47
citations ·
29
h-index
Lawrence Livermore National Laboratory
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training
2025 · 24 citations
Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models
2025 · 12 citations
TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention
2025 · 11 citations
The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages
2026
End-to-End Context Compression at Scale
2026
Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models
2025
The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text
2025
TruthPrInt: Mitigating LVLM Object Hallucination Via Latent Truthful-Guided Pre-Intervention
2025
Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training
2025
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
2025
The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text
2025
Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training
2025
Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models
2023
NEFTune: Noisy Embeddings Improve Instruction Finetuning
2023
SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning
2024
Topics
Training Techniques
Safety & Alignment
Evaluation
Efficiency
cs.LG
Fine-Tuning
Code
RLHF & Alignment
Vision-Language
Reinforcement Learning