Hugging Face Trending Papers
LatentPress: Context Compression Beyond Text and Vision
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv AI
Sep 2
LatentPress: Context Compression Beyond Text and Vision
LatentPress compresses conversational histories and long documents into continuous memory tokens that a frozen decoder can read directly, eliminating the need for text reconstruction at inference. The method achieves 4–16× compression with only a small adapter (0.1% of the decoder’s parameters) and outperforms text summaries and OCR-based compression on LongMemEval and LongBench-QA benchmarks. Writing and reading are significantly faster than traditional text summarization or OCR reconstruction, demonstrating a practical machine-facing context interface beyond text and vision.
arXiv AI
3d ago
Compress What You See, Not What You Say: Anchored Context Distillation for Latent-Observation Software Engineering Agents
The paper introduces LOHA, a context layout that compresses older tool observations into soft tokens while keeping the agent’s own turns and the last K observations in plain text, and ACD, a training method that distills full‑text predictions into this latent representation while anchoring behavior on plain text. This approach reduces context per call by up to 57% without significant loss in resolve rates, and improves instance throughput in single‑GPU serving. Experiments on SWE‑bench Verified show that K=3 yields a 43–57% compression with only modest performance impact, while larger windows favor task performance over compression.
Hugging Face Trending Papers
Jun 9
One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA
External memory effectively grounds large language models (LLMs) and vision-language models (VLMs)-based question answering (QA) in relevant multimodal evidence. However, existing memory paradigms represent each memory item in raw text and image forms, so retrieval-based systems must pass the retrieved text or images to the generation LLMs/VLMs, resulting in high token consumption and storage pressure, making it unaffordable for resource-constrained applications.
arXiv AI
Jun 10
One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA
arXiv:2606. 10572v1 Announce Type: new Abstract: External memory effectively grounds large language models (LLMs) and vision-language models (VLMs)-based question answering (QA) in relevant multimodal evidence.
arXiv AI
1d ago
FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution
arXiv:2609.36651v1 Announce Type: cross Abstract: Long-context reasoning in large language models incurs substantial computation and memory costs. Visual text compression (VTC) reduces input length b...
arXiv Computation and Language
Sep 1
When History Is Multimodal: Rethinking Context Management for Long-Horizon Agents
arXiv:2608.29897v1 Announce Type: new Abstract: Long-horizon agents need a context manager to compress growing interaction histories into a bounded working context, via passive strategies or active s...