THE INTERNET IS THINKING
Earlier sources: Language models
Language models learn patterns in text and other representations to predict or generate sequences. Follow model releases, training methods, reasoning, evaluation, and deployment research; a benchmark result is specific to its test conditions.
SYMTRI organizes observations from public sources into a living map. Connections reflect shared subject matter; they do not establish causation or endorse a source.
Open in the map ↗460 classified signals in the fourteen-day window. These counts include signals awaiting readable evidence.
Earlier sources
Up to ten sources with readable evidence, ordered by their feed timestamp. These archive sources can be older than the live fourteen-day window. This list is a sample, not a measure of total activity. Dates distinguish paper publication, repository creation, model/dataset activity, Hacker News posts, and KEV catalog additions. “First archived” records when SYMTRI first stored the signal.
- OpenAlex · Published · First archived
A Hybrid Deep Learning Approach for Early Detection of Wildfires Using Transformer Models and Feature Fusion Techniques ↗
Natural disasters, particularly wildfires, pose a serious threat to ecosystems, human lives, and infrastructure, making rapid and accurate fire detection essential for effective disaster management. Despite recent advances in deep learning-based wildfire detection, conventional CNN-based approaches are inherently limited in modeling long-range spatial dependencies, while relying on a single deep architecture may provide an incomplete representation of complex and multi-scale fire patterns. Furthermore, high-dimensional deep features may contain redundant information, increasing computational c…
- OpenAlex · Published · First archived
Segmentation-free hybrid CNN–transformer CAD framework with handcrafted feature fusion for explainable Leukaemia diagnosis ↗
Diagnosing leukaemia from microscopic blood smear images is nevertheless challenging for traditional Computer-Aided Diagnosis (CAD) systems. Many current methods depend on segmentation and basic feature representations. This makes it hard to tell apart morphologically similar subtypes. This work presents an extended hybrid CAD framework to address these limitations by fusing handcrafted texture descriptors, deep CNN representations, Transformer-based contextual modelling and explainable AI. Multi-resolution handcrafted features using the Discrete Wavelet Transform (DWT), Grey-Level Co-occurren…
- GitHub · Repository created · First archived
KKKKhazix/AIHOT ↗
一个自己找热点、自己写日报的网站框架。把信源和精选标准换成你的，它就是你的行业热点站。
- Hacker News · Posted on Hacker News · First archived
Check twice, cut once with LLM search relevance eval ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: LLMs Play Chicken in Realtime ↗
Was curious how LLMs would play chicken without a clear reward matrix, and then took it a step further by allowing communication and realtime decision making. Each LLM is in an independent loop, where each turn they are given the current speed and time to impact, as well as their historical latency. They can pre-plan moves to account for latency.
- Hacker News · Posted on Hacker News · First archived
10 Tokens for Your Meat Brain LLM ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
ESP32S3 cluster running 1.58-bit (BitNet) Language model ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
MicroLLM Lab – Try 7 tiny LLM's in the browser ↗
Hacker News discussion.
- arXiv · Published · First archived
Telescopic Language Models ↗
One deployed language model must often serve many compute budgets, yet serving each budget still means a separate training or compression run per point. We train a Telescopic Language Model (TLM) to be that continuum: a nested-capacity Transformer supervised by stochastic prefix supervision with a full anchor. At every step, one randomly truncated prefix of the capacity axis is trained against the full next-token target, alongside one full-capacity pass, so the trained artifact is a valid language model at every depth. Two forward-backward passes per step, no architectural change, nothing extr…
- arXiv · Published · First archived
Improving Test-Time Scaling with Adaptive Looped Transformers ↗
Looped transformers have demonstrated promising parameter efficiency by reusing layers for latent computation. Prior studies compare looped and non-looped models at matched parameters or per-token FLOPs. However, to the best of our knowledge, whether looping improves test-time scaling as outputs grow longer remains underexplored. Through post-training looped transformers, we study the accuracy-compute slope, measured as the accuracy gain per doubling of test-time decoding FLOPs. We find that existing looped transformers often yield steeper slopes than their non-looped baseline, yet underperfor…
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about Language models
Check each original source for its methods, release status, limitations, and supporting data. A repository announcement, a preprint, and a published study provide different kinds of evidence. SYMTRI’s subject classification helps discovery; it does not independently validate the source’s claims.
See the collection and counting methodology ↗ · Read the weekly synthesis ↗
Related threads
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.