ICML2023

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Lupin1998 authored a paper 16 days ago

OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers

Lupin1998 authored a paper 16 days ago

PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams

akhaliq submitted a paper 2 months ago

DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation

View all activity

Nymbo

posted an update 11 days ago

Post

5498

Introducing Inflect-v2, two exceptionally small, open-weight English TTS models at just 3.9M and 9.3M parameters. Both generate speech multiple times faster than real-time on CPU. Despite their size, Inflect-v2 delivers quality that is competitive with much larger lightweight TTS systems, including KittenTTS, Piper, and Supertonic-3.

CPU, CUDA, PyTorch, and ONNX are supported. Apache 2.0.

See it for yourselves:
owensong/Inflect-Micro-v2
owensong/Inflect-Nano-v2

Try the Demos:
Nymbo/Inflect-TTS (unlimited CPU usage)
owensong/Inflect-v2 (ultra-fast ZeroGPU usage)

6 replies

Lupin1998

authored 2 papers 16 days ago

OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers

Paper • 2607.04033 • Published Jul 4 • 76

PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams

Paper • 2606.07454 • Published Jun 5 • 14

abidlabs

posted an update about 1 month ago

Post

703

Uhh did Opus 4.8 cheat on PostTrainBench??

it found an API key in the PostTrainBench environment that allowed it to generate synthetic training data without using GPU hours, boosting the base model by 0.4913

Source: https://posttrainbench.com/traces/run.html?id=claude_non_api_max_claude-opus-4-8_10h_run1__healthbench_Qwen_Qwen3-4B-Base_17315102#tab=trace

1 reply

akhaliq

submitted 2 papers to Daily Papers 2 months ago

DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation

Paper • 2605.30350 • Published May 28 • 13

Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion

Paper • 2605.23346 • Published May 22

Lupin1998

authored 6 papers 2 months ago

Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora

Paper • 2604.24819 • Published Apr 27 • 91

Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists

Paper • 2604.28158 • Published Apr 30 • 49

NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation

Paper • 2605.10813 • Published May 11 • 16

PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents

Paper • 2605.10341 • Published May 11 • 35

PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control

Paper • 2605.15963 • Published May 15 • 17

RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution

Paper • 2605.21195 • Published May 20 • 20

akhaliq

submitted 2 papers to Daily Papers 3 months ago

optimize_anything: A Universal API for Optimizing any Text Parameter

Paper • 2605.19633 • Published May 19 • 6

Image Generators are Generalist Vision Learners

Paper • 2604.20329 • Published Apr 22 • 25

akhaliq

submitted 2 papers to Daily Papers 4 months ago

MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines

Paper • 2603.06679 • Published Mar 30 • 7

AVO: Agentic Variation Operators for Autonomous Evolutionary Search

Paper • 2603.24517 • Published Mar 25 • 11

akhaliq

submitted 2 papers to Daily Papers 5 months ago

V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising

Paper • 2603.16792 • Published Mar 17 • 3

Multimodal OCR: Parse Anything from Documents

Paper • 2603.13032 • Published Mar 13 • 46

Nymbo

posted an update 5 months ago

Post

7859

We should really have a release date range slider on the /models page. Tired of "trending/most downloaded" being the best way to sort and still seeing models from 2023 on the first page just because they're embedded in enterprise pipelines and get downloaded repeatedly. "Recently Created/Recently Updated" don't solve the discovery problem considering the amount of noise to sift through.

Slight caveat: Trending actually does have some recency bias, but it's not strong/precise enough.

3 replies

Lupin1998

authored a paper 5 months ago

The Trinity of Consistency as a Defining Principle for General World Models

Paper • 2602.23152 • Published Feb 26 • 203

AI & ML interests

Recent Activity

Team members 52

ICML2023's activity