AI

Feeds to Scour
SubscribedAll
Scoured 37 posts in 9.7 ms

Do We Want a Superintelligent People-Pleaser?

 🎮Game Engines
lesswrong.com·

Attention at the Theoretical Minimum: A Mathematics of Arrays Framework for Memory-Optimal Transformer Kernels

 🦾Rust ML  Content type: Academic
arxiv.org·

Sequential Data Poisoning in LLM Post-Training

 🕯️Candle  Content type: Academic
arxiv.org·

Principled Agent Debate: Adversarial Arbitration for Sycophancy Reduction in Large Language Models

 🕯️Candle  Content type: Academic
arxiv.org·

CodegenBench: Can LLMs Write Efficient Code Across Architectures?

 🧮Linear Algebra  Content type: Academic
arxiv.org··Hacker News

GenTI: Benchmarking LLMs for Autonomous IDPS Rule Generation for Unseen Attacks

 🏗️LLVM  Content type: Academic
arxiv.org·

StageFrontier: Synchronization-Aware Stage Accounting for Distributed ML Training

 🌍Distributed Systems  Content type: Academic
arxiv.org·

GenAutoML: An Agentic Framework for Dynamic Architecture Generation and Optimization in Time-Series Analysis

 🦾Rust ML  Content type: Academic
arxiv.org·

Sparse Mixture-of-Experts Reward Models Learn Interpretable and Specialized Experts for Personalized Preference Modeling

 🕯️Candle  Content type: Academic
arxiv.org·

SABLE: GPU-Based Power Flow Accelerator for Sparsity-Aware Batched Learning

 🌐WebGPU  Content type: Academic
arxiv.org·

BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization

 🎮Game Engines  Content type: Academic
arxiv.org·

nnAudio 2: Overcoming Dynamic Compilation Barriers and Transform Inconsistencies

 🦾Rust ML  Content type: Academic
arxiv.org·

GOTabPFN: From Feature Ordering to Compact Tokenization for Tabular Foundation Models on High-Dimensional Data

 🦾Rust ML  Content type: Academic
arxiv.org·

TensorBench: Benchmarking Coding Agents on a Compiler-Based Tensor Framework

 🕯️Candle  Content type: Academic
arxiv.org·

MimeLens: Position-Agnostic Content-Type Detection for Binary Fragments

 🦾Rust ML  Content type: Academic
arxiv.org·

StandardE2E: A Unified Framework for End-to-End Autonomous Driving Datasets

 🕯️Candle  Content type: Academic
arxiv.org·

Video-Rate Streaming Stylization on a Vision-Aware MLLM-Conditioned Edit Diffusion: Asymmetric Batched Inference on a Distilled UNet + MLLM Text Encoder

 🦾Rust ML  Content type: Academic
arxiv.org·

No more posts from bambolleo's subscribed feeds.

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