Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE
Sharpness-aware prompt evolution optimizes prompts for both performance and robustness by penalizing sharp regions in the prompt loss landscape, yielding prompts that transfer better across tasks and LLM families.
Apr 23, 2026
AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent
Distills multi-agent debate into one LLM through reasoning-enhanced fine-tuning, trajectory-based augmentation, and process-aware distillation, moving computation from inference to training.
Feb 3, 2026
SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding
We introduce SlideAgent, a versatile agentic framework for understanding multi-modal, multi-page, and multi-layout documents.
Nov 27, 2025
Protein Large Language Models: A Comprehensive Survey
A comprehensive survey of Protein Large Language Models, organizing the field along architectures, training objectives, datasets, and downstream tasks across biology, chemistry, and medicine.
Nov 1, 2025
Empowering Interdisciplinary Insights with Dynamic Graph Embedding Trajectories
DyGET converts temporal graph embeddings into interpretable trajectories that empower interdisciplinary insights through cross-disciplinary discovery and longitudinal community analysis.
Aug 25, 2025
A Survey on Efficient Large Language Model Training: From Data-centric Perspectives
A survey of efficient LLM training organized around data-centric techniques — selection, mixing, ordering, and synthesis — and their trade-offs with compute and downstream performance.
Jul 31, 2025
ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding
ProteinGPT is a multimodal LLM that integrates protein sequence and structural representations in a unified generative interface for property prediction and structure understanding.
Jul 18, 2025
ScreenLLM: Stateful Screen Schema for Efficient Action Understanding and Prediction
ScreenLLM introduces a stateful screen schema and key-frame extractor that compresses dynamic UI sessions into time-aware summaries, enabling efficient GUI understanding and action prediction with multimodal LLMs.
Apr 30, 2025
UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models
UniGuard is a universal safety guardrail for multimodal LLMs, defending against cross-modal jailbreak attacks across image and text channels with low utility cost.
Mar 3, 2025
SciEvo: A 2 Million, 30-Year Cross-disciplinary Dataset for Temporal Scientometric Analysis
SciEvo is a comprehensive dataset containing 2 million+ papers spanning 30 years (1995-2024) for temporal scientometric analysis.
Mar 3, 2025