Blog

262개 중 1-12번째 포스트

2026-05-24•7분•Paper Review

[논문 리뷰] Tokenisation via Convex Relaxations

Tokenisation is an integral part of the current NLP pipeline. Current tokenisation algorithms such as BPE and Unigram are greedy algorithms -- they make locally optimal decisions without considering t...

Paper Review

cs.CL

cs.LG

2026-05-24•8분•Paper Review

[논문 리뷰] Advancing Mathematics Research with AI-Driven Formal Proof Search

Large language models (LLMs) increasingly excel at mathematical reasoning, but their unreliability limits their utility in mathematics research. A mitigation is using LLMs to generate formal proofs in...

Paper Review

cs.AI

2026-05-24•16분•Paper Review

[논문 리뷰] Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning

Scaling test-time compute by iteratively updating a latent state has emerged as a powerful paradigm for reasoning. Yet the internal mechanisms that enable these iterative models to generalize beyond m...

Paper Review

cs.LG

2026-05-24•9분•Paper Review

[논문 리뷰] Hallucinations Undermine Trust; Metacognition is a Way Forward

Despite significant strides in factual reliability, errors -- often termed hallucinations -- remain a major concern for generative AI, especially as LLMs are increasingly expected to be helpful in mor...

Paper Review

cs.CL

2026-05-24•21분•Paper Review

[논문 리뷰] The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions

Scientific discovery is constrained not only by what is true, but by what is cognitively available to the researchers currently exploring a field. Many directions are coherent in light of the literatu...

Paper Review

cs.AI

cs.LG

2026-05-22•8분•Paper Review

[논문 리뷰] Generative Recursive Reasoning

How should future neural reasoning systems implement extended computation? Recursive Reasoning Models (RRMs) offer a promising alternative to autoregressive sequence extension by performing iterative ...

Paper Review

cs.AI

2026-05-22•9분•Paper Review

[논문 리뷰] Language Game: Talking to Non-Human Systems

Language carries thought and coordination among humans but rarely reaches further along the spectrum of diverse intelligence. Yet non-neural systems -- from gene regulatory networks and microbial cons...

Paper Review

cs.LG

2026-05-22•9분•Paper Review

[논문 리뷰] TRINITY: An Evolved LLM Coordinator

Combining diverse foundation models is promising, but weight-merging is limited by mismatched architectures and closed APIs. Trinity addresses this with a lightweight coordinator that orchestrates col...

Paper Review

cs.LG

2026-05-21•18분•Paper Review

[논문 리뷰] Code as Agent Harness

Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agent...

Paper Review

cs.CL

cs.AI

2026-05-18•7분•Paper Review

[논문 리뷰] MIRAGE: The Illusion of Visual Understanding

Multimodal AI systems have achieved remarkable performance across a broad range of real-world tasks, yet the mechanisms underlying visual-language reasoning remain surprisingly poorly understood. We r...

Paper Review

cs.AI

2026-05-18•16분•Paper Review

[논문 리뷰] ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment

Reinforcement Learning (RL) post-training alignment for language models is effective, but also costly and unstable in practice, owing to its complicated training process. To address this, we propose a...

Paper Review

cs.LG

2026-05-18•19분•Paper Review

[논문 리뷰] Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills

Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable re...

Paper Review

cs.AI

cs.CL

...