Feeds to Scour
SubscribedAll
Scoured 4880 posts in 11.1 ms
Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook  ✨LLMs
arxiv.org·1d
Show HN: ECX a 'Jail-Fix' for RLHF Neutrality Loops in LLMs  🕳LLM Vulnerabilities
zenodo.org·5d·Hacker News
Low-Rank Key Value Attention: Reducing KV Cache Memory and Maintaining Head Diversity  🤖LLM
fin.ai·17h·Hacker News
🥇Top AI Papers of the Week  🛡️AI Safety
nlp.elvissaravia.com·4d
AI Safety at the Frontier: Paper Highlights of February & March 2026  🛡️AI Safety
lesswrong.com·5d·Hacker News
Learning What Matters: Dynamic Dimension Selection and Aggregation for Interpretable Vision-Language Reward Modeling  ✨Gemini
arxiv.org·2d
Show HN: Pre-training, fine-tuning, and evals platform  ⚙️MLOps
oumi.ai·6d·Hacker News
Generalization Limits of Reinforcement Learning Alignment  🛡️AI Safety
arxiv.org·4d
Simulating the Evolution of Alignment and Values in Machine Intelligence  🛡️AI Safety
arxiv.org·2d
One Model for All: Multi-Objective Controllable Language Models  ✨LLMs
arxiv.org·3d
Mitigating Reward Hacking in RLHF via Advantage Sign Robustness  🛡️AI Security
arxiv.org·4d
TDA-RC: Task-Driven Alignment for Knowledge-Based Reasoning Chains in Large Language Models  🤖LLM
arxiv.org·2d
ARM: Advantage Reward Modeling for Long-Horizon Manipulation  ♟️Game Theory
arxiv.org·4d
TABQAWORLD: Optimizing Multimodal Reasoning for Multi-Turn Table Question Answering  ✨Gemini
arxiv.org·3d
Beyond Compromise: Pareto-Lenient Consensus for Efficient Multi-Preference LLM Alignment  🤖LLM
arxiv.org·2d
Beyond Semantic Manipulation: Token-Space Attacks on Reward Models  🛡️AI Security
arxiv.org·4d
UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning  🧠Agent Memory
arxiv.org·2d
Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents  🧠Agent Memory
arxiv.org·2d
Information as Structural Alignment: A Dynamical Theory of Continual Learning  🧠Agent Memory
arxiv.org·1d
Discrete Flow Matching Policy Optimization  📱Edge AI Optimization
arxiv.org·1d

Keyboard Shortcuts

Navigation
Next / previous item
j/k
Open post
oorEnter
Preview post
v
Post Actions
Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s
Recommendations
Add interest / feed
Enter
Not interested
x
Go to
Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help