Source-backed discovery
New Term Radar
Discover names and concepts appearing in public sources, with dated evidence, source coverage and comparable growth.
Saved terms stay in this browser and do not sync to your account. Source collection continues on the server without this page being open.
Collection coverage · Limited historyCurrent / previous observed days 7 / 4
Counts use complete UTC days. First observed means first seen by this collection, not when a term was coined.
Current window：2026-10-30 → 2026-11-06 (end excluded) · History 12 days
| Source | Current days | Previous days | Last success |
|---|---|---|---|
| arXiv | 6 | 4 | Nov 6, 2026, 12:30 AM UTC |
| arXiv | 7 | 3 | Nov 5, 2026, 10:01 AM UTC |
| Ask HN | 7 | 4 | Nov 5, 2026, 9:15 PM UTC |
| Ask HN | 7 | 4 | Nov 5, 2026, 8:30 PM UTC |
| Ask HN | 7 | 4 | Nov 5, 2026, 9:15 PM UTC |
| Ask HN | 7 | 4 | Nov 5, 2026, 9:15 PM UTC |
| GitHub | 7 | 4 | Nov 6, 2026, 12:30 AM UTC |
| GitHub Issues | 7 | 4 | Nov 5, 2026, 4:00 PM UTC |
| GitHub Releases | 7 | 2 | Nov 6, 2026, 12:15 AM UTC |
| GitHub | 7 | 4 | Nov 5, 2026, 2:30 PM UTC |
| GitHub Issues | 7 | 4 | Nov 5, 2026, 4:15 PM UTC |
| GitHub Releases | 7 | 4 | Nov 5, 2026, 4:15 PM UTC |
| GitHub | 7 | 4 | Nov 5, 2026, 2:30 PM UTC |
| GitHub Issues | 7 | 4 | Nov 5, 2026, 4:45 PM UTC |
| GitHub Releases | 7 | 4 | Nov 5, 2026, 4:15 PM UTC |
| GitHub Discovery | 1 | 0 | Nov 5, 2026, 9:15 PM UTC |
| GitHub Trending | 7 | 4 | Nov 6, 2026, 1:00 AM UTC |
| 7 | 3 | Nov 5, 2026, 10:00 AM UTC | |
| Hugging Face | 7 | 3 | Nov 5, 2026, 8:15 AM UTC |
| Hugging Face Spaces | 1 | 0 | Nov 5, 2026, 9:15 PM UTC |
| Hacker News | 7 | 4 | Nov 6, 2026, 1:00 AM UTC |
| Hacker News | 7 | 4 | Nov 5, 2026, 9:30 PM UTC |
| Hacker News | 7 | 4 | Nov 5, 2026, 9:30 PM UTC |
| Hacker News | 1 | 0 | Nov 5, 2026, 9:15 PM UTC |
| Show HN | 1 | 0 | Nov 5, 2026, 9:15 PM UTC |
| MIT News | 7 | 3 | Nov 5, 2026, 4:15 PM UTC |
| OpenAI | 7 | 4 | Nov 5, 2026, 11:30 AM UTC |
| Product Hunt | 7 | 4 | Nov 6, 2026, 1:00 AM UTC |
| 量子位 | 6 | 4 | Nov 4, 2026, 10:15 AM UTC |
| OpenRouter | 1 | 0 | Nov 6, 2026, 1:00 AM UTC |
| Hugging Face Models | 1 | 0 | Nov 6, 2026, 1:00 AM UTC |
| HF Daily Papers | 1 | 0 | Nov 6, 2026, 1:00 AM UTC |
| OpenRouter | 1 | 0 | Nov 6, 2026, 1:00 AM UTC |
| SEC EDGAR | 7 | 4 | Nov 5, 2026, 10:30 PM UTC |
| Sequoia Capital | 7 | 3 | Nov 5, 2026, 10:00 AM UTC |
| Simon Willison | 1 | 0 | Nov 5, 2026, 3:13 PM UTC |
| TechCrunch | 7 | 4 | Nov 5, 2026, 8:30 PM UTC |
| Contracts Finder | 7 | 4 | Nov 5, 2026, 7:45 PM UTC |
| V2EX | 7 | 4 | Nov 5, 2026, 8:30 PM UTC |
- Counts describe monitored public sources, not the whole web or search demand.
- Both weeks need adequate, comparable collection coverage.
Seven-day figures use the complete UTC window above. Priority is a research triage score, not search volume, market size or a probability of success.
FrontierPhysics
AI agents are playing an increasingly important role in physics research. However, existing physics benchmarks only evaluate fixed questions, isolated sub-tasks, or paper reproduction with given solutions, and rarely check research quality alongside correctness. We introduce FrontierPhysics, an end-to-end benchmark with 56 tasks made by 42 physicists based o
First observed Nov 5, 2026 · HF Daily Papers
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
Freeport Markets
Our proprietary AI finds the top onchain wallets to copy
First observed Nov 4, 2026 · Product Hunt
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
SFT
We introduce Dory1.0-4B, a 4-billion-parameter looped (latent-recurrent) language model with elastic depth: a single checkpoint serves different inference compute budgets. Dory1.0-4B is built on a normalized Transformer (nGPT) backbone with interleaved sliding-window and full-attention layers, organized into an input block, a shared recurrent block, and an o
First observed Oct 24, 2026 · HF Daily Papers / arXiv
- 7d mentions
- 1 previous 1
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
AGORA
arXiv:2611.05556v1 Announce Type: new Abstract: LLM-as-a-judge is a common substitute for costly human evaluation, and aggregating several judges is the standard remedy for any single judge's bias. Judge pools mix judges of very different reliability, while the human-labeled sets that validate them hold a few hundred items or fewer. In this regime the per-it
First observed Nov 5, 2026 · arXiv
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
BrainBind
arXiv:2611.05581v1 Announce Type: new Abstract: Real-world vision is dynamic and scene-rich, while EEG and fMRI resolve it at complementary temporal and spatial scales. Most neural decoding systems, however, align one modality in isolation and mostly against static images or short clips. We study the synchronized case: EEG and fMRI are recorded during the sa
First observed Nov 5, 2026 · arXiv
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
Gauge
Hi HN, I’m Evan from Gauge. We’re open-sourcing our CLI to recursively improve your docs for coding agents. The CLI includes a local execution backend, so you don't need an account to try it. Explainer video here: https://youtu.be/zhLUlIKB1Mg The CLI supports a hillclimbing loop: - set up tasks for coding agents that would need your docs, like 'set up Gauge
First observed Nov 5, 2026 · Hacker News
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
Fount
Fount uses TEEs through Tinfoil ( https://tinfoil.sh/ ) to provide provably confidential AI office agents. Think Cursor + Microsoft Office + Privacy.
First observed Nov 5, 2026 · Hacker News
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
-
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
OOD
Multi-teacher on-policy distillation (MOPD) extends on-policy distillation (OPD) to consolidate capabilities from multiple teachers. Although prior work reports near-perfect in-distribution (IND) distillation performance, we find that this can mask incomplete capability consolidation beyond the supervised distribution. A preliminary study on synthetic reason
First observed Nov 5, 2026 · HF Daily Papers
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
CIR
Composed Image Retrieval (CIR) aims to retrieve a target image given a reference image and a modification text. Although recent approaches leveraging Multimodal Large Language Models (MLLMs) have shown significant progress, we argue that the MLLM's compositional understanding remains underutilized. This stems from directly mapping composed queries into a ret
First observed Nov 5, 2026 · HF Daily Papers
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
T2I
In-image machine translation (IIMT) replaces text in an image with its translation while preserving the surrounding visual context. Existing task-specific models achieve convincing performance but require massive paired training images before and after translation. As advanced text-to-image (T2I) models have reached a practically usable level of multilingual
First observed Nov 5, 2026 · HF Daily Papers
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
webframe
Research: webframe: evaluated as a scraper and a sandbox webframe is a neat little project from Jeff Lindsay which lets you "run a web page like a program" - you point it at a URL or file and it executes it in a hidden headless web view and outputs console.log() to standard output and any exceptions to standard error. It's written in Go on top of the glaze l
First observed Nov 5, 2026 · Simon Willison
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 39 / 100
Embodsi
embodsi is a generative AI MMO experience that runs in the browser. It allows people to communicate (text, audio, video, avatar emotes and movement) and collaboratively build 3D spaces and games via LLMs connected to harnesses and sandboxes for object modeling, space layout, game logic, and driving persistent avatars with shared context and memory. It’s diff
First observed Nov 5, 2026 · Hacker News
- 7d mentions
- 0 previous 0
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 39 / 100
SleuthVLM
Omni models answer questions about videos by jointly processing sampled frames and audio in one turn, with progress driven largely by scaling model size and omni training data. We ask whether a model needs to hear the audio directly at all, and present SleuthVLM, an agent harness built on a VLM that never hears the audio directly: speech will be transcribed
First observed Nov 5, 2026 · HF Daily Papers
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
TSAD
Adversarial diffusion distillation has conventionally relied on image features for discrimination. We revisit this choice for multimodal diffusion transformers (MMDiTs), whose text stream becomes image-dependent through joint attention. We introduce Text-Stream Adversarial Distillation (TSAD), which exploits intermediate text-token states as a new adversaria
First observed Nov 5, 2026 · HF Daily Papers
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
Text-Stream Adversarial Distillation
Adversarial diffusion distillation has conventionally relied on image features for discrimination. We revisit this choice for multimodal diffusion transformers (MMDiTs), whose text stream becomes image-dependent through joint attention. We introduce Text-Stream Adversarial Distillation (TSAD), which exploits intermediate text-token states as a new adversaria
First observed Nov 5, 2026 · HF Daily Papers
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
PyRUA-DataFarm
Teleoperation remains the default way to collect robot demonstrations, but every episode costs robot and operator time, and every new task starts from scratch. We ask whether a coding agent can take over the teleoperator's job. In our DataFarm, the agent receives a data request and one calibration episode of the robot in the target scene and rebuilds the tas
First observed Nov 5, 2026 · HF Daily Papers
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
Magertron
First observed Nov 5, 2026 · Hacker News
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
VideoMemBench
Multimodal large language models (MLLMs) can now process hour-long videos, making extended multi-turn dialogue over a single video a natural mode of use. Sustaining such a dialogue requires more than answering each question in isolation: the model must retrieve and reuse information established earlier in the conversation, both what it has seen and what it h
First observed Nov 5, 2026 · HF Daily Papers
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
SDFT
Self-distillation methods for large language models with an exponential moving average (EMA) teacher already retain a history of student updates. Muon nevertheless stores a separate momentum buffer, increasing persistent training memory. We propose Muon with Reused Teacher (Muon-RT), which reuses the teacher-student displacement to eliminate momentum buffers
First observed Nov 5, 2026 · HF Daily Papers
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
fileForensics
Real or not? Check files before your AI trusts them.
First observed Nov 4, 2026 · Product Hunt
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 39 / 100
Hindsight Models and Inference API
Small, fast models for reranking, embeddings and decisions
First observed Nov 4, 2026 · Product Hunt
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
IIMT
In-image machine translation (IIMT) replaces text in an image with its translation while preserving the surrounding visual context. Existing task-specific models achieve convincing performance but require massive paired training images before and after translation. As advanced text-to-image (T2I) models have reached a practically usable level of multilingual
First observed Nov 5, 2026 · HF Daily Papers
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
Cinnamon
First observed Nov 5, 2026 · Hacker News
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
Engine-X
First observed Nov 5, 2026 · Show HN
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
-
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
Tokenome
First observed Nov 5, 2026 · Show HN
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
PyRUA-REAL
Coding agents powered by models such as GPT-6-Astra connect spatial reasoning with executable robot behavior, raising the question of how such agents can produce lasting improvements in robot capabilities from physical interaction. In this work, we study embodied recursive self-improvement (RSI) through real-world exploration, code refinement, and deployment
First observed Nov 5, 2026 · HF Daily Papers
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100
Wanaka Studio
Make and publish 3D games with the first AI game engine
First observed Nov 4, 2026 · Product Hunt
- 7d mentions
- 0 previous 1
- 7d sources
- 0
- 7d growth
- Not comparable
- Priority
- 39 / 100
SlackBench
arXiv:2611.05512v1 Announce Type: new Abstract: AI Agents are becoming digital coworkers that can browse the web, write code, run experiments, and assist humans over extended horizons. Yet existing benchmarks fall short of real knowledge work: many rely on synthetic data or isolated tasks, missing the complex, multi-party dynamics of collaborative projects,
First observed Nov 5, 2026 · arXiv
- 7d mentions
- 1 previous 0
- 7d sources
- 1
- 7d growth
- Not comparable
- Priority
- 39 / 100