Copertina

Charting Empirical Laws for LLM Fine-Tuning in Scientific Multi-Discipline Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Lintao, Lu, Zhuqiang, Zhu, Yilin, Hu, Kun, Yin, Zhenfei, Tang, Shixiang, Wang, Zhiyong, Ouyang, Wanli, Ma, Xinzhu
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens
di: Lu, Zhuqiang, et al.
Pubblicazione: (2024)

SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines
di: Wang, Yizhou, et al.
Pubblicazione: (2025)

CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming
di: Deng, Han, et al.
Pubblicazione: (2025)

Autoregressive Omni-Aware Outpainting for Open-Vocabulary 360-Degree Image Generation
di: Lu, Zhuqiang, et al.
Pubblicazione: (2023)

SciIF: Benchmarking Scientific Instruction Following Towards Rigorous Scientific Intelligence
di: Su, Encheng, et al.
Pubblicazione: (2026)

Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System
di: Su, Haoyang, et al.
Pubblicazione: (2024)

Towards an Effective Action-Region Tracking Framework for Fine-grained Video Action Recognition
di: Sun, Baoli, et al.
Pubblicazione: (2025)

CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation
di: Wu, Jianyu, et al.
Pubblicazione: (2025)

PhysUniBench: A Multi-Modal Physics Reasoning Benchmark at Undergraduate Level
di: Wang, Lintao, et al.
Pubblicazione: (2025)

UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines
di: Tang, Chen, et al.
Pubblicazione: (2025)

3D Object Detection from Images for Autonomous Driving: A Survey
di: Ma, Xinzhu, et al.
Pubblicazione: (2022)

MLLM-based Discovery of Intrinsic Coordinates and Governing Equations from High-Dimensional Data
di: Li, Ruikun, et al.
Pubblicazione: (2025)

Solving all laminar flows around airfoils all-at-once using a parametric neural network solver
di: Cao, Wenbo, et al.
Pubblicazione: (2025)

LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents
di: Li, Rui, et al.
Pubblicazione: (2025)

Pixel2Phys: Distilling Governing Laws from Visual Dynamics
di: Li, Ruikun, et al.
Pubblicazione: (2026)

S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering
di: Su, Encheng, et al.
Pubblicazione: (2026)

Human-Centric Foundation Models: Perception, Generation and Agentic Modeling
di: Tang, Shixiang, et al.
Pubblicazione: (2025)

AI-Driven Automation Can Become the Foundation of Next-Era Science of Science Research
di: Chen, Renqi, et al.
Pubblicazione: (2025)

SITransformer: Shared Information-Guided Transformer for Extreme Multimodal Summarization
di: Liu, Sicheng, et al.
Pubblicazione: (2024)

Text2Sign Diffusion: A Generative Approach for Gloss-Free Sign Language Production
di: Feng, Liqian, et al.
Pubblicazione: (2025)

Uni3D-LLM: Unifying Point Cloud Perception, Generation and Editing with Large Language Models
di: Liu, Dingning, et al.
Pubblicazione: (2024)

PredBench: Benchmarking Spatio-Temporal Prediction across Diverse Disciplines
di: Wang, ZiDong, et al.
Pubblicazione: (2024)

ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning
di: Xu, Wanghan, et al.
Pubblicazione: (2026)

NAS-LoRA: Empowering Parameter-Efficient Fine-Tuning for Visual Foundation Models with Searchable Adaptation
di: Chen, Renqi, et al.
Pubblicazione: (2025)

StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
di: Xue, Xiangyuan, et al.
Pubblicazione: (2026)

Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction
di: Ma, Xinzhu, et al.
Pubblicazione: (2025)

KAN Text to Vision? The Exploration of Kolmogorov-Arnold Networks for Multi-Scale Sequence-Based Pose Animation from Sign Language Notation
di: Du, Guanyi, et al.
Pubblicazione: (2026)

Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection
di: Zhang, Yinmin, et al.
Pubblicazione: (2021)

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
di: Chen, Zihong, et al.
Pubblicazione: (2025)

EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds
di: Chen, Lu, et al.
Pubblicazione: (2025)

ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition
di: Liu, Yujie, et al.
Pubblicazione: (2025)

Referring Video Object Segmentation with Cross-Modality Proxy Queries
di: Sun, Baoli, et al.
Pubblicazione: (2025)

ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks
di: Zhou, Heng, et al.
Pubblicazione: (2025)

Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts
di: Hu, Zixuan, et al.
Pubblicazione: (2025)

Reassessing the Role of Supervised Fine-Tuning: An Empirical Study in VLM Reasoning
di: Yu, Yongcan, et al.
Pubblicazione: (2025)

Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code
di: Shin, Jiho, et al.
Pubblicazione: (2023)

Owl-AuraID 1.0: An Intelligent System for Autonomous Scientific Instrumentation and Scientific Data Analysis
di: Deng, Han, et al.
Pubblicazione: (2026)

Interleaving Reasoning for Better Text-to-Image Generation
di: Huang, Wenxuan, et al.
Pubblicazione: (2025)

Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE
di: Chen, Zeren, et al.
Pubblicazione: (2023)

MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search
di: Yang, Zonglin, et al.
Pubblicazione: (2025)