Blog | SuanLab

283개 중 1-12번째 포스트

2026-10-05•16분•Paper Review

[논문 리뷰] TabFM-Auto: Self-Evolving Pipelines for Tabular Foundation Models

Tabular foundation models achieve strong zero-shot accuracy on structured data by pretraining on synthetic tables, but they ignore the column names, task descriptions, and auxiliary files that carry d...

Paper Review

cs.LG

2026-10-03•16분•Paper Review

[논문 리뷰] The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

On-policy distillation (OPD) trains a student to match the teacher's next-token distributions on the student's own trajectories and has yielded substantial empirical gains. Generalized variants allow ...

Paper Review

cs.LG

2026-06-26•9분•Paper Review

[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...

Paper Review

cs.LG

cs.AI

2026-06-24•7분•Paper Review

[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...

Paper Review

cs.CL

2026-06-24•7분•Paper Review

[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)...

Paper Review

stat.ML

cs.LG

2026-06-24•9분•Paper Review

[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...

Paper Review

cs.AI

cs.CL

2026-06-22•11분•Paper Review

[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...

Paper Review

cs.LG

cs.AI

2026-06-13•20분•Paper Review

[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...

Paper Review

cs.AI

cs.CY

2026-06-13•7분•Paper Review

[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...

Paper Review

cs.CL

cs.AI

2026-06-07•9분•Paper Review

[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...

Paper Review

cs.AI

cs.CL

2026-06-07•18분•Paper Review

[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...

Paper Review

cs.AI

cond-mat.mtrl-sci

2026-06-07•8분•Paper Review

[논문 리뷰] Memory Caching: RNNs with Growing Memory

Paper Review

cs.LG

cs.AI

...