AI Research

Feeds to Scour
SubscribedAll
Scoured 182 posts in 6.8 ms

Depth over Fidelity in Fixed-Budget Noisy Evolution Strategies

 🧠LLMs  Content type: Academic
arxiv.org·

Towards Diverse Scientific Hypothesis Search with Large Language Models

 🧠LLMs  Content type: Academic
arxiv.org·

Pseudospectral Bounds for Transient Amplification in Coupled Gradient Descent

 🧠LLMs  Content type: Academic
arxiv.org·

Robust Regression of General ReLUs with Queries

 📜CS Papers  Content type: Academic
arxiv.org·

Minibatch Selection via Partition Matroid Constrained Gradient Matching

 🧠LLMs  Content type: Academic
arxiv.org·

In Defense of Information Leakage in Concept-based Models

 🧠LLMs  Content type: Academic
arxiv.org·

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?

 ⚙️MLOps  Content type: Academic
arxiv.org·

Gradient Descent with Large Step Size Restores Symmetry in Deep Linear Networks with Multi-Pathway

 ⚙️MLOps  Content type: Academic
arxiv.org·

RKSC: Reasoning-Aware KV Cache Sharing and Confident Early Exit for Multi-Step LLM Inference

 🧠LLMs  Content type: Academic
arxiv.org·

Position: Don't Just "Fix it in Post": A Science of AI Must Study Training Dynamics

 🛡️AI Safety  Content type: Academic
arxiv.org·

Efficiently Learning Drifting Halfspaces with Massart Noise

 ⚙️MLOps  Content type: Academic
arxiv.org·

Asymptotic Optimality of the High-Dimensional Gaussian Mechanism and Improved Low-Dimensional Mechanisms for Differential Privacy

 🔢Quantitative Finance  Content type: Academic
arxiv.org·

Ekka: Automated Diagnosis of Silent Errors in LLM Inference

 🧠LLMs  Content type: Academic
arxiv.org·

Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding

 ⚙️MLOps  Content type: Academic
arxiv.org·

DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling

 🤖AI  Content type: Academic
arxiv.org·

Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers

 🧠LLMs  Content type: Academic
arxiv.org·

Interactions Between Crosscoder Features: A Compact Proofs Perspective

 📜CS Papers  Content type: Academic
arxiv.org·

Generative Modeling of Discrete Latent Structures via Dynamic Policy Gradients

 ⚙️MLOps  Content type: Academic
arxiv.org·

When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models

 🧠LLMs  Content type: Academic
arxiv.org·

LIMMT: Less is More for Motion Tracking

 ⚙️MLOps  Content type: Academic
arxiv.org·
Sign up or log in to see more results

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