Image de couverture de livre

Lost in Tokenization: Context as the Key to Unlocking Biomolecular Understanding in Scientific LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhuang, Kai, Zhang, Jiawei, Liu, Yumou, Cao, Hanqun, Gu, Chunbin, Liu, Mengdi, Gao, Zhangyang, Wang, Zitong Jerry, Zhou, Xuanhe, Heng, Pheng-Ann, Wu, Lijun, He, Conghui, Tan, Cheng
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Unlocking Potential Binders: Multimodal Pretraining DEL-Fusion for Denoising DNA-Encoded Libraries
par: Gu, Chunbin, et autres
Publié: (2024)

CONFIDE: Hallucination Assessment for Reliable Biomolecular Structure Prediction and Design
par: Gao, Zijun, et autres
Publié: (2025)

DEL-Ranking: Ranking-Correction Denoising Framework for Elucidating Molecular Affinities in DNA-Encoded Libraries
par: Cao, Hanqun, et autres
Publié: (2024)

CA-DEL: An Open Multi-Target, Multi-Modal Benchmark for Learning from DNA-Encoded Library Screens
par: He, Mutian, et autres
Publié: (2026)

Does Engram Do Memory Retrieval in Autoregressive Image Generation?
par: Wang, Jinghao, et autres
Publié: (2026)

Lightweight MSA Design Advances Protein Folding From Evolutionary Embeddings
par: Cao, Hanqun, et autres
Publié: (2025)

RiboSphere: Learning Unified and Efficient Representations of RNA Structures
par: Zhang, Zhou, et autres
Publié: (2026)

Learning the PTM Code through a Coarse-to-Fine, Mechanism-Aware Framework
par: Zhang, Jingjie, et autres
Publié: (2025)

Bi-TEAM: A Unified Cross-Scale Representation Learning Framework for Chemically Modified Biomolecules
par: Gu, Chunbin, et autres
Publié: (2026)

SAGEPhos: Sage Bio-Coupled and Augmented Fusion for Phosphorylation Site Detection
par: Zhang, Jingjie, et autres
Publié: (2025)

TD3B: Transition-Directed Discrete Diffusion for Allosteric Binder Generation
par: Cao, Hanqun, et autres
Publié: (2026)

Unlocking Positive Transfer in Incrementally Learning Surgical Instruments: A Self-reflection Hierarchical Prompt Framework
par: Zhu, Yu, et autres
Publié: (2026)

A deep reinforcement learning platform for antibiotic discovery
par: Cao, Hanqun, et autres
Publié: (2025)

GeoCycler: Reward-Aligned 3D Diffusion for Constraint-Conditioned Cyclic Peptide Design
par: Zhang, Jingjie, et autres
Publié: (2026)

Creating Virtual Environments with 3D Gaussian Splatting: A Comparative Study
par: Qiu, Shi, et autres
Publié: (2025)

Advancing Extended Reality with 3D Gaussian Splatting: Innovations and Prospects
par: Qiu, Shi, et autres
Publié: (2024)

ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both
par: Guo, Ziyu, et autres
Publié: (2026)

ODesign: A World Model for Biomolecular Interaction Design
par: Zhang, Odin, et autres
Publié: (2025)

ChemMiner: A Large Language Model Agent System for Chemical Literature Data Mining
par: Chen, Kexin, et autres
Publié: (2024)

SciTS: Scientific Time Series Understanding and Generation with LLMs
par: Wu, Wen, et autres
Publié: (2025)

SciVerse: Unveiling the Knowledge Comprehension and Visual Reasoning of LMMs on Multi-modal Scientific Problems
par: Guo, Ziyu, et autres
Publié: (2025)

Point Cloud Understanding via Attention-Driven Contrastive Learning
par: Wang, Yi, et autres
Publié: (2024)

MM-Mixing: Multi-Modal Mixing Alignment for 3D Understanding
par: Wang, Jiaze, et autres
Publié: (2024)

CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning
par: Cui, Hao, et autres
Publié: (2025)

PARM: Pipeline-Adapted Reward Model
par: Fan, Xingyu, et autres
Publié: (2026)

The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility?
par: Zhang, Yiyi, et autres
Publié: (2025)

Testing Properties of Edge Distributions
par: Fei, Yumou
Publié: (2026)

Unbounded-width CSPs are Untestable in a Sublinear Number of Queries
par: Fei, Yumou
Publié: (2025)

LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs
par: Liu, Xiaoran, et autres
Publié: (2025)

Evaluating DNA function understanding in genomic language models using evolutionarily implausible sequences
par: Jiang, Shiyu, et autres
Publié: (2025)

Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning
par: Li, Lanqing, et autres
Publié: (2024)

Two-State Spin Systems with Negative Interactions
par: Fei, Yumou, et autres
Publié: (2023)

Towards Synchronous Memorizability and Generalizability with Site-Modulated Diffusion Replay for Cross-Site Continual Segmentation
par: Xu, Dunyuan, et autres
Publié: (2024)

Unifying Physically-Informed Weather Priors in A Single Model for Image Restoration Across Multiple Adverse Weather Conditions
par: Xu, Jiaqi, et autres
Publié: (2026)

Cross-modality Guidance-aided Multi-modal Learning with Dual Attention for MRI Brain Tumor Grading
par: Xu, Dunyuan, et autres
Publié: (2024)

Comprehensive Generative Replay for Task-Incremental Segmentation with Concurrent Appearance and Semantic Forgetting
par: Li, Wei, et autres
Publié: (2024)

Memory-Efficient Prompt Tuning for Incremental Histopathology Classification
par: Zhu, Yu, et autres
Publié: (2024)

Lost in Time: Clock and Calendar Understanding Challenges in Multimodal LLMs
par: Saxena, Rohit, et autres
Publié: (2025)

EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning
par: Xing, Zhenghao, et autres
Publié: (2025)

Less Data Less Tokens: Multilingual Unification Learning for Efficient Test-Time Reasoning in LLMs
par: Chen, Kang, et autres
Publié: (2025)