Deep Learning

Feeds to Scour
SubscribedAll
Scoured 134 posts in 12.3 ms

AgentCompile: An LLM-Guided Compiler for Direct CUDA Inference

 ⚡CUDA  Content type: Academic
arxiv.org·

mingusb/transformer-golf: The Fully Unrolled Transformer: An experimental repository for architecture simplification and compilation. [2026]

 🧠Neural Networks  Content type: Code
github.com··Hacker News

Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles

 🤖Data science  Content type: Academic
arxiv.org·

The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show

 🧠Neural Networks  Content type: Academic
arxiv.org·

apple/coreai-models: Model export recipes, Python primitives, and Swift runtime utilities for on-device AI

 🤖Data science  Content type: Code
github.com··Hacker News

Efficient Time Series Clustering from Multiscale Reservoir Dynamics with Granular-Ball Anchoring Graph Optimization

 🧠Neural Networks  Content type: Academic
arxiv.org·

Adv-TGD: Adversarial Text-Guided Diffusion for Face Recognition Impersonation Attacks

 🎯Fine-tuning  Content type: Academic
arxiv.org·

Phantom transitions in language model fine-tuning

 🎯Fine-tuning  Content type: Academic
arxiv.org·

Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit Correction

 🎮Reinforcement Learning  Content type: Academic
arxiv.org·

Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs

 🧠LLMs  Content type: Academic
arxiv.org·

Towards Robust Arabic Speech Emotion Recognition with Deep Learning

 🧠Neural Networks  Content type: Academic
arxiv.org·

FreeAnimate: Training-Free Human Image Animation with Preview-Guided Denoising

 🧠Transformers  Content type: Academic
arxiv.org·

Characterizing Software Aging in GPU-Based LLM Serving Systems

 🧠LLM Inference  Content type: Academic
arxiv.org·

Spiking Neural Network inference on FPGAs with hls4ml

 🤖Machine Learning  Content type: Academic
arxiv.org·

The Score Hamiltonian: Mapping Diffusion Models to Adiabatic Transport

 🎮Reinforcement Learning  Content type: Academic
arxiv.org·

BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression

 🧠LLMs  Content type: Academic
arxiv.org·

AutoMegaKernel: A Statically-Checked Agent Harness for Self-Retargeting Megakernel Synthesis

 ⚡CUDA  Content type: Academic
arxiv.org··Hacker News

DiBS: Diffusion-Informed Branch Selection

 🤖Machine Learning  Content type: Academic
arxiv.org·

Forward-Only Convolutional Neural Networks with Learnable Channel-Class Assignment

 🧠Neural Networks  Content type: Academic
arxiv.org·

Optimality of FSQ Tokens for Continuous Diffusion for Categorical Data with Application to Text-to-Speech

 💬Natural Language Processing  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