frozen-model

Tag

Cards List
#frozen-model

Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence

Hugging Face Daily Papers · 4d ago Cached

This paper introduces Spatial Memory Agent (SMA), a runtime framework that improves frozen vision-language models' spatial reasoning through verifier-guided reflection and reusable memory without parameter updates or external tools, achieving strong results across five benchmarks and four base VLMs.

0 favorites 0 likes
#frozen-model

Show HN: A 6M-token movable window on a single 46GB GPU

Hacker News Top · 2026-07-28 Cached

This paper presents a frozen 12B model that uses a persistent memory of verified solutions to achieve 100% accuracy on solved problem families with zero generation tokens, and demonstrates a 6M-token movable window on a single 46GB GPU.

0 favorites 0 likes
#frozen-model

A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever

Hugging Face Daily Papers · 2026-07-26 Cached

A frozen 12B parameter model augmented with a persistent memory of verified solutions achieves 100% accuracy on over 180 instances across nine problem families with zero generation tokens, bit-exact deterministic outputs, outperforming frontier models on those solved tasks while using negligible compute.

0 favorites 0 likes
#frozen-model

@akshay_pachaar: Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open…

X AI KOLs Following · 2026-07-03 Cached

The article discusses a Hugging Face experiment where an automated loop rewrites only the code (harness) around a frozen model, raising its benchmark score from 0% to near Sonnet 4.6 at lower cost, demonstrating that many benchmark failures stem from the harness, not the model itself.

0 favorites 0 likes
#frozen-model

@dair_ai: // δ-mem: Efficient Online Memory for LLMs // One of the more elegant memory mechanisms I've seen this month. Most long…

X AI KOLs Following · 2026-05-13 Cached

The paper introduces δ-mem, a lightweight online memory mechanism that augments frozen LLMs with a compact associative memory state updated by delta-rule learning, achieving significant improvements on memory-heavy benchmarks without fine-tuning or context extension.

0 favorites 0 likes
← Back to home

Submit Feedback