Claude Fable 5.2, Inference Performance Index: changing the way we measure inference capacity, a paper on Tools Need Not Speak in Text: Latent Context Compression for Agents, and many more!
Firehose
Filtered to Companies, tagged “deep learning” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives
Browse by tag
This article provides a fine-tuning guide for 3D generation models, specifically TRELLIS.2, using low-rank adaptation (LoRA). The model is fine-tuned on a subset of the Google Scanned Objects (GSO) dataset, which has 188 footwear objects. The fine-tuning process involves adding LoRA adapters to the sparse-structure flow DiT and the shape flow DiT, which control the object's shape and geometry. The adapters are trained using a rectified flow matching objective, and the original model weights are kept frozen. The fine-tuning script and containers are available for local and Hugging Face Jobs deployment. AI summary
Token pooling-aware training for multi-vector embedding models improves retrieval quality by teaching the encoder to preserve information when its vectors are merged, helping to retrieve better from the same storage budget. By applying a loss wrapper to a multi-vector retrieval loss, pooling-aware training can be used with existing models, resulting in a 97.8% retention of unpooled NanoBEIR nDCG@10 with a 4x reduction in document vectors. AI summary