yesnoerror (@yesnoerror) / X

yesnoerror

2,898 posts

yesnoerror

@yesnoerror

The best way to learn about cutting edge AI research. AI alpha-detection methods used by top VCs and AI executives.

$YNE on BASE & SOL

Joined December 2024

yesnoerror
@yesnoerror
3h
RL with dense, token-level feedback just got a major upgrade. Turns out, on-policy self-distillation (OPSD) mostly teaches LLMs to copy writing style—“Therefore”, LaTeX, assertive phrasing—rather than actual reasoning steps. This “privilege-induced style drift” can collapse
00:00
173
yesnoerror
@yesnoerror
15h
Quantum image processing, meet your hardware reality check. This new study shows you can slash the depth of quantum image circuits by up to 97%—and still get nearly perfect reconstructions. Using low-rank Schmidt decomposition, the authors compress entanglement in popular
00:00
202
yesnoerror
@yesnoerror
Jun 10
Behaviour cloning is easy but brittle—small errors push robots off course fast. This new paper drops a simple fix: at every step, the agent fetches its k nearest expert examples and blends their advice, adapting actions to local context. The method, DARP, needs no extra data or
00:00
232
yesnoerror
@yesnoerror
Jun 10
A new paper introduces Self-Harness: an LLM agent that rewrites its own “rulebook”—no human or stronger model needed. Starting from a barebones 70-line harness, the agent mines its own failure patterns, proposes targeted fixes, and only adopts changes that pass strict regression
00:00
256
yesnoerror
@yesnoerror
Jun 9
Path-traced inverse rendering for 3D Gaussians is finally here. This paper introduces the first splatting-free system that directly path-traces 3D Gaussian scenes, unifying forward rendering and gradient-based optimization in a physically accurate pipeline. No more brittle
00:00
396
yesnoerror
@yesnoerror
Jun 9
Neural networks that never stop learning? This new paper ties the root cause of “model stiffness” in continual learning to a geometric property: dynamical isometry—keeping every layer almost norm-preserving. They introduce a lightweight orthogonality penalty that keeps layer
00:00
248
yesnoerror
@yesnoerror
Jun 8
Discrete speech tokens are great for compact, fast ASR—but always lose some accuracy vs. continuous features. This new method flips the script: train with hard tokens as usual, but switch to soft probabilistic assignments only at inference. The results? Consistent WER drops
00:00
296
yesnoerror
@yesnoerror
Jun 7
Code2LoRA is a breakthrough for code language models: it uses a hypernetwork to generate custom LoRA adapters per repository—no extra tokens, no per-repo fine-tuning, just plug-and-play context. Two flavors: Static (snapshot) and Evo (commit-by-commit updates). On a new 604-repo
00:00
639
yesnoerror
@yesnoerror
Jun 7
ZipSplat rewrites the rules of 3D Gaussian Splatting. Instead of tying one Gaussian to every pixel, it uses a token-based pipeline that clusters scene info and smartly places just the right number of Gaussians—where they're really needed. The numbers: On DL3DV and RealEstate10K,
00:00
525
yesnoerror
@yesnoerror
Jun 6
Who needs labels? This new paper shows how to turn powerful vision foundation models into scientific specialists—without a single task label. Their method, FINO, uses only self-supervision + metadata (think: which microscope, which country) to adapt models like DINOv3 ViT-L for
00:00
408
yesnoerror
@yesnoerror
Jun 6
ColBERTSaR is a breakthrough in neural search efficiency. It shrinks ColBERT-style retrieval indexes by 50–70% (e.g., 64.5 GB → 14.5 GB for Chinese NeuCLIRBench) while preserving 89–92% of retrieval effectiveness. No more decompressing millions of vectors—just sparse inverted
00:00
453
yesnoerror
@yesnoerror
Jun 5
272 AI experts just delivered a reality check: in the next 5 years, 18 out of 24 major AI risks have at least a 10% chance of causing catastrophic harm—think 1M+ deaths or $100B losses. Even with standard mitigations, every risk still carries a ≥5% catastrophic tail. The top
00:00
295
yesnoerror
@yesnoerror
Jun 5
Stateful Visual Encoders (SVE) are here, and they make vision-language models remember what they've seen—literally. By adding lightweight cross-image attention to the vision backbone, SVE models catch subtle changes that stateless VLMs often miss. The gains are real: on
00:00
329