Blog
257개 중 1-12번째 포스트
![[논문 리뷰] Generative Recursive Reasoning](/assets/images/blog/20260522-paper-2605-19376-generative-recursive-reasoning.jpg)
[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 ...
![[논문 리뷰] Language Game: Talking to Non-Human Systems](/assets/images/blog/20260522-paper-2605-16321-language-game-talking-to-non-h.jpg)
[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...
![[논문 리뷰] TRINITY: An Evolved LLM Coordinator](/assets/images/blog/20260522-paper-2512-04695-trinity-an-evolved-llm-coordin.jpg)
[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...
![[논문 리뷰] Code as Agent Harness](/assets/images/blog/20260521-paper-2605-18747-code-as-agent-harness.jpg)
[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...
![[논문 리뷰] MIRAGE: The Illusion of Visual Understanding](/assets/images/blog/20260518-paper-2603-21687-mirage-the-illusion-of-visual-.jpg)
[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...
![[논문 리뷰] ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment](/assets/images/blog/20260518-paper-2601-21484-ets-energy-guided-test-time-sc.jpg)
[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...
![[논문 리뷰] Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills](/assets/images/blog/20260518-paper-2512-16301-adaptation-of-agentic-ai-a-sur.jpg)
[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...
![[논문 리뷰] GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models](/assets/images/blog/20260518-paper-2410-05229-gsm-symbolic-understanding-the.jpg)
[논문 리뷰] GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
Recent advancements in Large Language Models (LLMs) have sparked interest in their formal reasoning capabilities, particularly in mathematics. The GSM8K benchmark is widely used to assess the mathemat...
![[논문 리뷰] Compressed Convolutional Attention: Efficient Attention in a Compressed Latent Space](/assets/images/blog/20260516-paper-2510-04476-compressed-convolutional-atten.jpg)
[논문 리뷰] Compressed Convolutional Attention: Efficient Attention in a Compressed Latent Space
Multi-headed Attention's (MHA) quadratic compute and linearly growing KV-cache make long-context transformers expensive to train and serve. Prior works such as Grouped Query Attention (GQA) and Multi-...
![[논문 리뷰] Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models](/assets/images/blog/20260515-paper-2605-07721-memory-efficient-looped-transf.jpg)
[논문 리뷰] Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
Recurrent LLM architectures have emerged as a promising approach for improving reasoning, as they enable multi-step computation in the embedding space without generating intermediate tokens. Models su...
![[논문 리뷰] AI co-mathematician: Accelerating mathematicians with agentic AI](/assets/images/blog/20260515-paper-2605-06651-ai-co-mathematician-accelerati.jpg)
[논문 리뷰] AI co-mathematician: Accelerating mathematicians with agentic AI
We introduce the AI co-mathematician, a workbench for mathematicians to interactively leverage AI agents to pursue open-ended research. The AI co-mathematician is optimized to provide holistic support...
![[논문 리뷰] Functional Post-Clustering Selective Inference with Applications to EHR Data Analysis](/assets/images/blog/20260515-paper-2405-03042-functional-post-clustering-sel.jpg)
[논문 리뷰] Functional Post-Clustering Selective Inference with Applications to EHR Data Analysis
In electronic health records (EHR) analysis, clustering patients according to patterns in their data is crucial for uncovering new subtypes of diseases. Existing medical literature often relies on cla...