A quick glance at another bunch of codecs
codecs.multimedia.cx·4d
🎬Cinema Codecs
State-of-the-art image generation Leonardo models and text-to-speech Deepgram models now available in Workers AI
blog.cloudflare.com·9h
🎙️Whisper
Why are CUDA kernels hard to optimize?
johndcook.com·28m
🧮Compute Optimization
Regarding formatting issues with AI-generated copy
dev.to·17h·
Discuss: DEV
✅Format Verification
Flatness-aware Curriculum Learning via Adversarial Difficulty
arxiv.org·19h
📊Learned Metrics
The Mind's Eye: A Multi-Faceted Reward Framework for Guiding Visual Metaphor Generation
arxiv.org·19h
🏛Digital humanities
Apparently it's easy to detect LLM-generated text now
papers.ssrn.com·4h·
Discuss: Hacker News
🔍Information Retrieval
SWiFT: Soft-Mask Weight Fine-tuning for Bias Mitigation
arxiv.org·19h
📊Rate-Distortion Theory
DualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction
arxiv.org·19h
⧗Information Bottleneck
Long-Term Variability in Physiological-Arousal Relationships for Robust Emotion Estimation
arxiv.org·19h
👁️Perceptual Coding
Autoregressive Universal Video Segmentation Model
arxiv.org·19h
📊Rate-Distortion Theory
Neural networks of the mouse visceromotor cortex
nature.com·23h
🧠Learned Codecs
Heartbreak as a Service?
syntheticauth.ai·4h·
Discuss: Hacker News
🏛Digital humanities
ROSE: Remove Objects with Side Effects in Videos
arxiv.org·19h
⟷Bidirectional Programming
Disentangling Polysemantic Neurons with a Null-Calibrated Polysemanticity Index and Causal Patch Interventions
arxiv.org·1d
🔍Vector Forensics
An Efficient Dual-Line Decoder Network with Multi-Scale Convolutional Attention for Multi-organ Segmentation
arxiv.org·1d
📊Learned Metrics
RDDM: Practicing RAW Domain Diffusion Model for Real-world Image Restoration
arxiv.org·19h
🖼️JPEG XL
Show HN: A short story on developing a long-context World-Model with no money
francesco215.github.io·5d·
Discuss: Hacker News
🧠Learned Codecs
Everything I Studied to Become a Machine Learning Engineer (No CS Background)
towardsdatascience.com·5h
🧠Machine Learning
OwlCap: Harmonizing Motion-Detail for Video Captioning via HMD-270K and Caption Set Equivalence Reward
arxiv.org·19h
🧠Learned Codecs