Cover Image

Motif-2-12.7B-Reasoning: A Practitioner's Guide to RL Training Recipes

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lim, Junghwan, Lee, Sungmin, Kim, Dongseok, Kim, Taehyun, Park, Eunhwan, Lee, Jeesoo, Lee, Jeongdoo, Lee, Junhyeok, Cheung, Wai Ting, Choi, Dahye, Ha, Minsu, Her, Jaeheui, Huh, Jaeyeon, Jung, Hanbin, Kang, Changjin, Kim, Beomgyu, Kim, Minjae, Kim, Taewhan, Kim, Youngrok, Kweon, Hyukjin, Lee, Haesol, Lee, Kungyu, Oh, Dongpin, Park, Yeongjae, Ryu, Bokki, Weon, Dongjoo
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Motif 2 12.7B technical report
by: Lim, Junghwan, et al.
Published: (2025)

Motif-Video 2B: Technical Report
by: Lim, Junghwan, et al.
Published: (2026)

Motif 2.6B Technical Report
by: Lim, Junghwan, et al.
Published: (2025)

Grouped Differential Attention
by: Lim, Junghwan, et al.
Published: (2025)

Expanding Foundational Language Capabilities in Open-Source LLMs through a Korean Case Study
by: Lim, Junghwan, et al.
Published: (2025)

Latent-Space Mean-Field Theory for Deep BitNet-like Training: Constrained Gradient Flows with Smooth Quantization and STE Limits
by: Kim, Dongwon, et al.
Published: (2025)

Super Monotonic Alignment Search
by: Lee, Junhyeok, et al.
Published: (2024)

Development of an Agentic AI Model for NGS Downstream Analysis Targeting Researchers with Limited Biological Background
by: Lee, Donghyeon, et al.
Published: (2025)

IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning
by: Lee, Soeun, et al.
Published: (2024)

ViPCap: Retrieval Text-Based Visual Prompts for Lightweight Image Captioning
by: Kim, Taewhan, et al.
Published: (2024)

Emerging Photon Jets in the Hadronic Calorimeter: A Novel Signature of Neutral Long-Lived Particles at the LHC
by: Kim, Jinheung, et al.
Published: (2025)

Simple arithmetic operation in latent space can generate a novel three dimensional graph metamaterials
by: Kim, Namjung, et al.
Published: (2024)

Improved Decoupled Control of Modular Multilevel Converter under Constaint of Nearest Level Modulation via Disturbance Observer Design
by: Park, Jaeyeon, et al.
Published: (2025)

Training-free LLM Verification via Recycling Few-shot Examples
by: Lee, Dongseok, et al.
Published: (2025)

P‐75: Extreme Low Power a‐InGaZnO TFT Scan Driver with Extra Clock Signal Modulation
by: Hyunwoo Kim, et al.
Published: (2024)

QuadStretcher: A Forearm-Worn Skin Stretch Display for Bare-Hand Interaction in AR/VR
by: Kim, Taejun, et al.
Published: (2025)

MATANet: A Multi-context Attention and Taxonomy-Aware Network for Fine-Grained Underwater Recognition of Marine Species
by: Lee, Donghwan, et al.
Published: (2026)

Learning-augmented robotic automation for real-world manufacturing
by: Kim, Yunho, et al.
Published: (2026)

Black hole/quantum machine learning correspondence
by: Lee, Jae-Weon, et al.
Published: (2025)

KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge
by: Lee, Jiyoung, et al.
Published: (2024)

Learning Semantic Information from Raw Audio Signal Using Both Contextual and Phonetic Representations
by: Kim, Jaeyeon, et al.
Published: (2024)

V-NAW: Video-based Noise-aware Adaptive Weighting for Facial Expression Recognition
by: Lee, JunGyu, et al.
Published: (2025)

SDS KoPub VDR: A Benchmark Dataset for Visual Document Retrieval in Korean Public Documents
by: Lee, Jaehoon, et al.
Published: (2025)

A Panoramic Study of $K$-Factors for 111 Processes at the 14 TeV LHC
by: Kim, Dongjoo, et al.
Published: (2024)

State-of-Health Prediction for EV Lithium-Ion Batteries via DLinear and Robust Explainable Feature Selection
by: Kim, Minsu, et al.
Published: (2025)

Let Multimodal Embedders Learn When to Augment Query via Adaptive Query Augmentation
by: Kim, Wongyu, et al.
Published: (2025)

Autonomously Designed Pulses for Precise, Site-Selective Control of Atomic Qubits
by: Park, Sanghyo, et al.
Published: (2025)

How do leisure activities impact leisure domain and life domain satisfaction and subjective well‐being?
by: Dohee Kim, et al.
Published: (2024)

Charitable giving under the behavioral influence of income inequality: Evidence from South Korea
by: Youngrok Kim
Published: (2025)

Liouville-type theorems for Lane--Emden inequalities involving nonlocal operators
by: Kim, T., et al.
Published: (2026)

Development of high‐performance silk‐based composite films with enhanced thermal conductivity and EMI shielding effectiveness
by: Jaekyung Lee, et al.
Published: (2025)

Coding-Free and Privacy-Preserving Agentic Framework for Data-Driven Clinical Research
by: Kim, Taehun, et al.
Published: (2026)

When Is Enough Not Enough? Illusory Completion in Search Agents
by: Ko, Dayoon, et al.
Published: (2026)

Multi-step Strong First-Order Electroweak Phase Transitions in the Inverted Type-I 2HDM: Parameter Space, Gravitational Waves, and Collider Phenomenology
by: Lee, Soojin, et al.
Published: (2025)

LDI, A Lipid Droplet Inhibitor, Disrupts Lipid Accumulation and Modulates Hepatic Lipid Profiles in Fatty Liver (Adv. Mater. 7/2026)
by: Seunghee Kim, et al.
Published: (2026)

LDI, A Lipid Droplet Inhibitor, Disrupts Lipid Accumulation and Modulates Hepatic Lipid Profiles in Fatty Liver
by: Seunghee Kim, et al.
Published: (2025)

Progresses and Perspectives of 1D Soft Sensing Devices for Healthcare Applications
by: Jinho Kim, et al.
Published: (2024)

Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues
by: Kim, Youngmin, et al.
Published: (2025)

SynC: Synthetic Image Caption Dataset Refinement with One-to-many Mapping for Zero-shot Image Captioning
by: Kim, Si-Woo, et al.
Published: (2025)

DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party Dialogues
by: Jang, Kyochul, et al.
Published: (2025)