The Scene Language: Representing Scenes with Programs, Words, and Embeddings https://
ai.stanford.edu/~yzzhang/proje
cts/scene-language/
… https://
arxiv.org/abs/2410.16770
a visual scene representation that concisely and precisely describes the structure, semantics, and identity of visual scenes.
@jiajunwu_cs
@jiqizhixin
-
Scene Language: Stanford’s Visual Scene Representation Framework
By
–
-
OpenCoder: Top-Tier Open Source Code Language Model
By
–
Introducing OpenCoder, a Fully Open Code LLM. https://
arxiv.org/abs/2411.04905 https://
opencoder-llm.github.io a top-tier code LLM that not only achieves performance comparable to leading models but also serves as an "open cookbook" for the research community. -
Alibaba Qwen Releases Qwen2.5-Coder-32B-Instruct Model
By
–
introducing Qwen2.5-Coder-32B-Instruct released by @Alibaba_Qwen
-
MIT Introduces Deep Generative Models Class 6.S978
By
–
Introducint kaiming he’s new “deep generative models” class 6.s978 https://
mit-6s978.github.io -
AFlow: Automating Agentic Workflow Generation by MetaGPT
By
–
Introducing AFlow: Automating Agentic Workflow Generation by MetaGPT https://
arxiv.org/abs/2410.10762 https://
github.com/geekan/MetaGPT
/tree/main/examples/aflow
… -
FAN: Fourier Analysis Networks for Periodic Phenomena Modeling
By
–
FAN: Fourier Analysis Networks https://
arxiv.org/pdf/2410.02675
.pdf
… https://
github.com/YihongDong/FAN
introducing FAN, a novel network architecture based on Fourier Analysis, which empowers the ability to efficiently model and reason about periodic phenomena. -
TableGPT2: Unprecedented Scale Table-Trained Language Model
By
–
Introducing TableGPT2, a model rigorously pre-trained and finetuned with over 593.8K tables and 2.36M high quality query-table-output tuples, a scale of table-related data unprecedented in prior research.
-
TableGPT2: Large Multimodal Model for Tabular Data
By
–
TableGPT2: A Large Multimodal Model with Tabular Data Integration https://
arxiv.org/pdf/2411.02059
TableGPT Agent：
https://
github.com/tablegpt/table
gpt-agent
…
Hugging Face： -
Hunyuan-Large: 389B Parameter Open-Source MoE Model
By
–
introduc ing Hunyuan-Large, which is currently the largest open-source Transformer-based mixture of experts model, with a total of 389 billion parameters and 52 billion activation parameters, capable of handling up to 256K tokens.
-
Tencent Releases Hunyuan-Large Open-Source MoE Model
By
–
Tencent released Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters https://
llm.hunyuan.tencent.com https://
github.com/Tencent/Hunyua
n-Large
… https://
huggingface.co/tencent/Hunyua
n-Large/tree/main
… https://
huggingface.co/spaces/tencent
/Hunyuan-Large
… https://
arxiv.org/abs/2411.02265