AI Research

Feeds to Scour
SubscribedAll
Scoured 198 posts in 6.0 ms

Phantom transitions in language model fine-tuning

 🧠LLMs  Content type: Academic
arxiv.org·

zulman/peer-review: A panel of AI agents that peer-reviews your document and hands back an improved version.

 🤖AI Agents  Content type: Code
github.com··Hacker News

Attention Based Interpretability With Concept Transformer

 🗄️Vector Databases  Content type: Blog
medium.com
·

Why LLMs hallucinate?

 🧠LLMs  Content type: Blog
medium.com
·

Data Synthesis and Parameter-Efficient Fine-Tuning for Low-Resource NMT: A Case Study on Q'eqchi' Mayan

 🏠Self-Hosting  Content type: Academic
arxiv.org·

Gaming AI-Assisted Peer Reviews Poses New Risks to the Scientific Community

 📱Edge AI  Content type: Academic
arxiv.org·

Towards Robust Arabic Speech Emotion Recognition with Deep Learning

 📱Edge AI  Content type: Academic
arxiv.org·

Review the Code, Not the Story: A Vision and Protocol for Code-First Peer Review

 🔍Static Analysis  Content type: Academic
arxiv.org·

Importance-Aware Scheduling for High-Dimensional Hyperparameter Optimization

 ⏱️Tokio  Content type: Academic
arxiv.org·

The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans

 🤖AI Agents  Content type: Academic
arxiv.org·

Self-supervised Learning Matters: A Simple Ensemble Solution for Micro-Gesture Recognition

 📱Edge AI  Content type: Academic
arxiv.org·

Transformer Based Model for Spatiotemporal Feature Learning in EEG Emotion Recognition

 🗄️Vector Databases  Content type: Academic
arxiv.org·

Towards Tight Bounds for Streaming Attention

 🗄️Vector Databases  Content type: Academic
arxiv.org·

StepPRM-RTL: Stepwise Process-Reward Guided LLM Fine-Tuning for Enhanced RTL Synthesis

 🔌Hardware  Content type: Academic
arxiv.org·

PatchSTG: Scalable Spatiotemporal Graph Transformers for Traffic Forecasting on Irregular Sensor Networks

 📱Edge AI  Content type: Academic
arxiv.org·

Ablation Study of Block Size, Weight Precision, and Scale Precision in NVFP4 Inference for Low-Power Edge-Efficient Neural Networks

 📱Edge Computing  Content type: Academic
arxiv.org·

Evaluating Research-Level Math Proofs via Strict Step-Level Verification

 🤖AI Agents  Content type: Academic
arxiv.org·

PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers on Overleaf

 🔍RAG  Content type: Academic
arxiv.org·

The State of Peer Review in Empirical Software Engineering: A Community Survey on Review Load, Quality, and GenAI Use

 🔍Static Analysis  Content type: Academic
arxiv.org·

PENet+: A Lightweight Residual Transformer Framework for Efficient Image Steganalysis

 🔍RAG  Content type: Academic
arxiv.org·

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