I'm soft-launching my Obsidian archive of whitepapers. It's AI/LLM paper excerpts plus questions and topical connections. Feedback requested!
Sample: Can dialogue systems track both speakers' beliefs across turns?
https://t.co/fCV9aCpcis
ReasoningFlow maps LLM reasoning traces into fine-grained DAGs, revealing the hidden discourse structure behind backtracking, self-correction, and verification.
- Across five models and three task types, reasoning traces show surprisingly similar structural patterns despite different training data and base models.
- Fine-grained behaviors like local verification, self-reflection, and assumptions are now identifiable, enabling better monitoring of the reasoning process.
- Most erroneous steps in LRM traces never actually contribute to the final answer — they are structural dead ends.
- Mechanistic causal dependencies between reasoning steps do not match the surface-level language discourse structure, suggesting traces can mislead.
Lines of inquiry it opens:
- Can reasoning traces prove models are actually reasoning versus mimicking?
- Why do reasoning models produce unfaithful or unhelpful reasoning traces?
- Why does reflection in reasoning models mostly confirm the first answer?
https://t.co/2byenuIXpn
@jinulee_v
@jinulee_v I'll add your paper to my collection, but check this out. I matched on it and it exposes interesting "Inquiring Lines" of related research.
https://t.co/KY2LKaBPvL
@deepfates You might find research using this - I've connected a limited (~1750 paper excerpts) collection with Inquiring Lines that thread related research across the collection:
https://t.co/inr1VpByAF
Every sign at this refinery in Ireland is in russian. The official website is a .RU domain.
There’s no reason to hide it because local politicians are openly doing it for them.
@MatthewBerman Been watching your tube for, well, 2 yrs? See if you find this interesting - explore LLM research with "inquiring lines" - topical questions and concepts across domains. I built this from my own Arxiv Obsidian archive. https://t.co/dErAeoHZYq
Anthropic just published When AI Builds Itself
Read between the lines and dig below the surface with Inquiring Lines:
Recursive self-improvement is no longer purely theoretical — here's where we actually stand.
- AI systems are beginning to automate meaningful parts of the research pipeline, from ideation to experimentation.
- Progress toward recursive self-improvement is real but uneven, with key bottlenecks remaining in verification and novelty.
- The implications of AI accelerating its own development raise urgent questions about oversight, autonomy, and the pace of change.
Lines of inquiry it opens:
- Can humans build reliable oversight for increasingly complex AI systems?
- What implicit alignment do humans provide by staying in research loops?
- Which failure modes dominate in autonomous research agents? https://t.co/U9ziPQw48D
.@NielsRogge Would love for you check this out. I've had a personal collection of white papers excerpted in Obsidian for years, and just moved it online. It's only 1700 or so LLM-specific papers. But I've created a faceted explorer that offers "Inquiring Lines" into related research by cross-cutting, tension-surfacing, synthesizing, and frontier-opening research.
https://t.co/Ixuxy2DoxU
@burkov I matched on this paper in my Arxiv archive and pulled up some interesting related research, and new "Inquiring Lines" for exploration.
https://t.co/8KEAnhMmHd
Featured Paper: Learn from your own latents and not from tokens: A sample-complexity theory
Predicting your own latent representations beats token-level learning by an exponential factor in sample complexity — here's the theory behind why.
- For compositional data modeled as a probabilistic context-free grammar of depth L, supervised and token-level self-supervised learning require exponentially many samples in L to recover the latent structure; latent prediction needs only a constant number (up to log factors).
- This result is confirmed via a hierarchical clustering algorithm, an end-to-end neural network performing latent prediction at each level, and the first formal sample-complexity analysis of data2vec.
- data2vec is shown to implicitly perform hierarchical latent prediction, and explicit stacking as in H-JEPA is found to be largely redundant.
Lines of inquiry it opens:
- How do hidden embeddings preserve more information than discrete tokens?
- Do latent sequence vectors outperform per-token latent iterative computation for reasoning?
- Can latent space represent reasoning dimensions that text cannot?
https://t.co/wmjCxBhx6U
@drfeifei I searched "Language models have given machines an extraordinary command of concepts, vocabulary, and reasoning, but the physical world, virtual or real, runs on a different substrate."
World models may model the world. Language makes it meaningful.
https://t.co/0qYyN83puF
@askalphaxiv This paper is too fresh for me to have it embedded yet, but it surfaces new Inquiring Lines of related research exploration, for those journeying through the never-ending field of LLM innovation.
https://t.co/jFccpScrqQ
What if you could explore AI whitepapers by lines of inquiry? Like research that cuts across categories? Tensions surfaced by contradictory findings? Research that synthesizes insights or opens new directions?
Check out new Inquiring Lines w faceted exploration. Link in reply.
What if you could explore AI whitepapers by lines of inquiry? Like research that cuts across categories? Tensions surfaced by contradictory findings? Research that synthesizes insights or opens new directions?
Check out new Inquiring Lines w faceted exploration. Link in reply.