Blog
281개 중 1-12번째 포스트
![[논문 리뷰] RePo: Language Models with Context Re-Positioning](/assets/images/blog/20260626-paper-2512-14391-repo-language-models-with-cont.jpg)
[논문 리뷰] RePo: Language Models with Context Re-Positioning
In-context learning is fundamental to modern Large Language Models (LLMs); however, prevailing architectures impose a rigid and fixed contextual structure by assigning linear or constant positional in...
![[논문 리뷰] Self-Harness: Harnesses That Improve Themselves](/assets/images/blog/20260624-paper-2606-09498-self-harness-harnesses-that-im.jpg)
[논문 리뷰] Self-Harness: Harnesses That Improve Themselves
The performance of LLM-based agents is jointly shaped by their base models and the harnesses that mediate their interaction with the environment. Because different models exhibit distinct behaviors, e...
![[논문 리뷰] When Does LeJEPA Learn a World Model?](/assets/images/blog/20260624-paper-2605-26379-when-does-lejepa-learn-a-world.jpg)
[논문 리뷰] When Does LeJEPA Learn a World Model?
A representation that scrambles the true degrees of freedom of the world cannot support reliable planning or compositional generalization. We prove that LeJEPA (alignment plus Gaussian regularization)...
![[논문 리뷰] SkillOpt: Executive Strategy for Self-Evolving Agent Skills](/assets/images/blog/20260624-paper-2605-23904-skillopt-executive-strategy-fo.jpg)
[논문 리뷰] SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning optimizer for the skill, and none of which reli...
![[논문 리뷰] Memory Caching: RNNs with Growing Memory](/assets/images/blog/20260622-paper-2602-24281-memory-caching-rnns-with-growi.jpg)
[논문 리뷰] Memory Caching: RNNs with Growing Memory
Transformers have been established as the de-facto backbones for most recent advances in sequence modeling, mainly due to their growing memory capacity that scales with the context length. While plaus...
![[논문 리뷰] From AGI to ASI](/assets/images/blog/20260613-paper-2606-12683-from-agi-to-asi.jpg)
[논문 리뷰] From AGI to ASI
Over the last decade, building human-level artificial general intelligence has moved from far-fetched speculation to being a concrete next-decade target for many of the largest AI organisations. Achie...
![[논문 리뷰] End-to-End Context Compression at Scale](/assets/images/blog/20260613-paper-2606-09659-end-to-end-context-compression.jpg)
[논문 리뷰] End-to-End Context Compression at Scale
Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. Recent techniques to compress the KV cache fall short: they either degrade model quality sub...
![[논문 리뷰] LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization](/assets/images/blog/20260607-paper-2606-05400-leanmarathon-toward-reliable-a.jpg)
[논문 리뷰] LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization
Long-horizon autoformalization of research mathematics fails not only at hard lemmas, but at scale: statements drift, dependencies tangle, context decays, and local repairs corrupt distant work. We pr...
![[논문 리뷰] Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence](/assets/images/blog/20260607-paper-2606-01444-self-revising-discovery-system.jpg)
[논문 리뷰] Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence
Scientific discovery is not only answer generation but revision of the representational regime in which evidence, artifacts, operations, and verifiers are typed. We develop a category-theoretic accoun...
![[논문 리뷰] Memory Caching: RNNs with Growing Memory](/assets/images/blog/20260607-paper-2602-24281-memory-caching-rnns-with-growi.jpg)
[논문 리뷰] Memory Caching: RNNs with Growing Memory
Transformers have been established as the de-facto backbones for most recent advances in sequence modeling, mainly due to their growing memory capacity that scales with the context length. While plaus...
![[논문 리뷰] From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning](/assets/images/blog/20260607-paper-2505-17117-from-tokens-to-thoughts-how-ll.jpg)
[논문 리뷰] From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
Humans organize knowledge into compact conceptual categories that balance compression with semantic richness. Large Language Models (LLMs) exhibit impressive linguistic abilities, but whether they nav...
![[논문 리뷰] LT2: Linear-Time Looped Transformers](/assets/images/blog/20260603-paper-2605-20670-lt2-linear-time-looped-transfo.jpg)
[논문 리뷰] LT2: Linear-Time Looped Transformers
Looped Transformers (LT) have emerged as a powerful architecture by iterating their layers multiple times before decoding the final token. However, pairing them with full attention retains quadratic c...