[논문리뷰] The Station: An Open-World Environment for AI-Driven Discoverywydu이 arXiv에 게시한 'The Station: An Open-World Environment for AI-Driven Discovery' 논문에 대한 자세한 리뷰입니다.#Review#Multi-Agent System#Open-World Environment#Scientific Discovery#AI-Driven Research#Large Language Models#Emergent Behavior#State-of-the-Art (SOTA)2025년 11월 10일댓글 수 로딩 중
[논문리뷰] Teaching Pretrained Language Models to Think Deeper with Retrofitted RecurrencearXiv에 게시된 'Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence' 논문에 대한 자세한 리뷰입니다.#Review#Recurrent Language Models#Pretrained Models#Model Surgery#Curriculum Learning#Test-Time Compute Scaling#Mathematics Reasoning#Efficient Training#Depth Recurrence2025년 11월 10일댓글 수 로딩 중
[논문리뷰] SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy OptimizationarXiv에 게시된 'SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization' 논문에 대한 자세한 리뷰입니다.#Review#LLM#Reinforcement Learning#Soft-Thinking#Gumbel Reparameterization#Policy Optimization#Chain-of-Thought (CoT)#GRPO2025년 11월 10일댓글 수 로딩 중
[논문리뷰] SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?Ofir Press이 arXiv에 게시한 'SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?' 논문에 대한 자세한 리뷰입니다.#Review#소프트웨어 성능 최적화#언어 모델#저장소 수준 추론#벤치마크#실제 워크로드#코드 정확성#속도 향상#코드 최적화2025년 11월 10일댓글 수 로딩 중
[논문리뷰] Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMsZiyue Li이 arXiv에 게시한 'Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs' 논문에 대한 자세한 리뷰입니다.#Review#Mixture-of-Experts (MoE)#Large Language Models (LLMs)#Router Optimization#Manifold Regularization#Generalization#Post-training Fine-tuning#Task Embedding Alignment2025년 11월 10일댓글 수 로딩 중
[논문리뷰] Robot Learning from a Physical World ModelarXiv에 게시된 'Robot Learning from a Physical World Model' 논문에 대한 자세한 리뷰입니다.#Review#Robot Learning#Video Generation#Physical World Model#Reinforcement Learning#Zero-shot Manipulation#Object-Centric Learning#Sim-to-Real2025년 11월 10일댓글 수 로딩 중
[논문리뷰] Reinforcement Learning Improves Traversal of Hierarchical Knowledge in LLMsarXiv에 게시된 'Reinforcement Learning Improves Traversal of Hierarchical Knowledge in LLMs' 논문에 대한 자세한 리뷰입니다.#Review#Reinforcement Learning#Large Language Models#Hierarchical Knowledge#Knowledge Traversal#Structured Prompting#Internal Representations#Alignment Tax2025년 11월 10일댓글 수 로딩 중
[논문리뷰] RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking ServicesZijie Meng이 arXiv에 게시한 'RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services' 논문에 대한 자세한 리뷰입니다.#Review#LLM Post-Training#Domain Adaptation#Social Networking Services#Reinforcement Learning#Supervised Fine-Tuning#Catastrophic Forgetting#Data Efficiency2025년 11월 10일댓글 수 로딩 중
[논문리뷰] Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty HeadsJiaheng Zhang이 arXiv에 게시한 'Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads' 논문에 대한 자세한 리뷰입니다.#Review#LLM Reasoning Verification#Uncertainty Quantification (UQ)#UHeads#Process Reward Models (PRMs)#Chain-of-Thought (CoT)#Self-Supervised Learning#Computational Efficiency#Domain Generalization2025년 11월 10일댓글 수 로딩 중
[논문리뷰] RLoop: An Self-Improving Framework for Reinforcement Learning with Iterative Policy InitializationWenhao Huang이 arXiv에 게시한 'RLoop: An Self-Improving Framework for Reinforcement Learning with Iterative Policy Initialization' 논문에 대한 자세한 리뷰입니다.#Review#Reinforcement Learning#LLMs#Generalization#Overfitting#Catastrophic Forgetting#Iterative Policy Optimization#Policy Diversity2025년 11월 10일댓글 수 로딩 중
[논문리뷰] RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable EnvironmentsShuyue Stella Li이 arXiv에 게시한 'RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments' 논문에 대한 자세한 리뷰입니다.#Review#Reinforcement Learning#Language Models#Adaptive Environments#Verifiable Environments#Procedural Generation#Curriculum Learning#Generalization2025년 11월 10일댓글 수 로딩 중
[논문리뷰] Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language ModelsarXiv에 게시된 'Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language Models' 논문에 대한 자세한 리뷰입니다.#Review#Multimodal Speech Recognition#Large Language Models#Audio-Visual Speech Recognition#LoRA#Matryoshka Representation Learning#Elastic Inference#Parameter-Efficient Adaptation2025년 11월 10일댓글 수 로딩 중
[논문리뷰] NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS ModelingarXiv에 게시된 'NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modeling' 논문에 대한 자세한 리뷰입니다.#Review#Text-to-CAD#NURBS Modeling#Large Language Models#Geometric Deep Learning#Boundary Representation#Hybrid Representation#CAD Generation2025년 11월 10일댓글 수 로딩 중
[논문리뷰] MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMsarXiv에 게시된 'MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs' 논문에 대한 자세한 리뷰입니다.#Review#Multimodal Large Language Models (MLLMs)#Multi-Video Understanding#Evaluation Benchmark#Video Perception#Video Reasoning#Sports Analytics#Autonomous Driving2025년 11월 10일댓글 수 로딩 중
[논문리뷰] MPJudge: Towards Perceptual Assessment of Music-Induced PaintingsarXiv에 게시된 'MPJudge: Towards Perceptual Assessment of Music-Induced Paintings' 논문에 대한 자세한 리뷰입니다.#Review#Music-Painting Cross-Modal#Perceptual Assessment#Modality-Adaptive Normalization#Direct Preference Optimization#Cross-Modal Fusion#Dataset Annotation#Affective Computing2025년 11월 10일댓글 수 로딩 중
[논문리뷰] Long Grounded Thoughts: Distilling Compositional Visual Reasoning Chains at ScalearXiv에 게시된 'Long Grounded Thoughts: Distilling Compositional Visual Reasoning Chains at Scale' 논문에 대한 자세한 리뷰입니다.#Review#Visual Reasoning#Compositional AI#Vision-Language Models#Data Synthesis#Chain-of-Thought#Reinforcement Learning#Multimodal Transfer#Grounded Reasoning2025년 11월 10일댓글 수 로딩 중
[논문리뷰] Llama-Embed-Nemotron-8B: A Universal Text Embedding Model for Multilingual and Cross-Lingual TasksarXiv에 게시된 'Llama-Embed-Nemotron-8B: A Universal Text Embedding Model for Multilingual and Cross-Lingual Tasks' 논문에 대한 자세한 리뷰입니다.#Review#Text Embedding#Multilingual#Cross-Lingual#Contrastive Learning#Model Merging#Synthetic Data Generation#Instruction-Tuning#LLM2025년 11월 10일댓글 수 로딩 중
[논문리뷰] LUT-LLM: Efficient Large Language Model Inference with Memory-based Computations on FPGAsJason Cong이 arXiv에 게시한 'LUT-LLM: Efficient Large Language Model Inference with Memory-based Computations on FPGAs' 논문에 대한 자세한 리뷰입니다.#Review#FPGA#Large Language Models (LLM)#Inference Optimization#Memory-based Computation#Vector Quantization#Table Lookup#Hardware Acceleration2025년 11월 10일댓글 수 로딩 중
[논문리뷰] IterResearch: Rethinking Long-Horizon Agents via Markovian State ReconstructionHaotian Xu이 arXiv에 게시한 'IterResearch: Rethinking Long-Horizon Agents via Markovian State Reconstruction' 논문에 대한 자세한 리뷰입니다.#Review#Long-Horizon Agents#Markov Decision Process#Workspace Reconstruction#Reinforcement Learning#Context Management#Iterative Deep Research#LLM Agents#Efficiency-Aware Policy Optimization2025년 11월 10일댓글 수 로딩 중
[논문리뷰] HaluMem: Evaluating Hallucinations in Memory Systems of AgentsarXiv에 게시된 'HaluMem: Evaluating Hallucinations in Memory Systems of Agents' 논문에 대한 자세한 리뷰입니다.#Review#Memory Systems#AI Agents#Hallucination Detection#Evaluation Benchmark#Long-term Memory#Memory Extraction#Memory Updating#Question Answering2025년 11월 10일댓글 수 로딩 중