Kaichen Zhang (@kaichenzhang358) 's Twitter Profile
Kaichen Zhang

@kaichenzhang358

student at NTU@sg

ID: 1788365212980301824

linkhttps://kcz358.github.io calendar_today09-05-2024 00:27:57

38 Tweet

49 Followers

34 Following

Li Bo (@boli68567011) 's Twitter Profile Photo

SAE Made Easy github.com/EvolvingLMMs-L… Sparse Autoencoders (SAE) have become a cornerstone in the field of explainable AI, powering safety and interpretability research at leading labs like Anthropic, OpenAI, and Google. Despite their effectiveness, training SAEs has

SAE Made Easy

github.com/EvolvingLMMs-L…

Sparse Autoencoders (SAE) have become a cornerstone in the field of explainable AI, powering safety and interpretability research at leading labs like Anthropic, OpenAI, and Google. 

Despite their effectiveness, training SAEs has
Li Bo (@boli68567011) 's Twitter Profile Photo

😻 LMMs-Eval upgrades to v0.4, better evals for better models. - multi-node evals, tp+dp parallel. - new doc_to_message support for interleaved modalities inputs, fully compatible with OpenAI official message format, suitable for evaluation in more complicated tasks. - unified

😻 LMMs-Eval upgrades to v0.4, better evals for better models.
- multi-node evals, tp+dp parallel.
- new doc_to_message support for interleaved modalities inputs, fully compatible with OpenAI official message format, suitable for evaluation in more complicated tasks.
- unified
Li Bo (@boli68567011) 's Twitter Profile Photo

Throughout my journey in developing multimodal models, I’ve always wanted a framework that lets me plug & play modality encoders/decoders on top of an auto-regressive LLM. I want to prototype fast, try new architectures, and have my demo files scale effortlessly — with full

Kaichen Zhang (@kaichenzhang358) 's Twitter Profile Photo

🚀 Releasing LMMs Engine by EvolvingLMMs‑Lab — a lean, flexible framework for any-to-any modality pretraining & fine-tuning. 🔧 Built with cutting-edge optimizations: FSDP2, Ulysses Sequence Parallel, Flash Attention 2 📚 Dive in: github.com/EvolvingLMMs-L…

Ziwei Liu (@liuziwei7) 's Twitter Profile Photo

🔥One-Stop Training Engine for Unified Models🔥 ⚡️LMMs-Engine⚡️ is a lean and flexible unified model training engine built for hacking at scale * Support multimodal inputs and outputs, from AR, diffusion and linear models, to unified models like BAGEL 🏠github.com/EvolvingLMMs-L…

🔥One-Stop Training Engine for Unified Models🔥

⚡️LMMs-Engine⚡️ is a lean and flexible unified model training engine built for hacking at scale

* Support multimodal inputs and outputs, from AR, diffusion and linear models, to unified models like BAGEL

🏠github.com/EvolvingLMMs-L…
Nathan Lambert (@natolambert) 's Twitter Profile Photo

Love to see more fully open post-training recipes (this one multimodal reasoning). It's surprising how rare post-training data is because the opportunity for impact is huge. Lots of people will try it and simple data methods still can improve on SOTA.

Lidong Bing (@lidongbing) 's Twitter Profile Photo

🔥 Introducing LongVT: Teaching Multimodal LLMs to "Actively Look Back" and understand long videos just like humans! We tackle the "sparse evidence" & "hallucination" issues in long-video reasoning with an end-to-end Agentic solution. Project: evolvinglmms-lab.github.io/LongVT/ Paper:

Ziwei Liu (@liuziwei7) 's Twitter Profile Photo

Our open-source tools and models have become trusted infrastructure for the global AI community, with representative repos including: 🚂 LMMs-Engine: github.com/EvolvingLMMs-L… 📊 LMMs-Eval: github.com/EvolvingLMMs-L… 🤖 LLaVA-OneVision-1.5: github.com/EvolvingLMMs-L…

Our open-source tools and models have become trusted infrastructure for the global AI community, with representative repos including:

🚂 LMMs-Engine: github.com/EvolvingLMMs-L…
📊 LMMs-Eval: github.com/EvolvingLMMs-L…
🤖 LLaVA-OneVision-1.5: github.com/EvolvingLMMs-L…