1 citations · 1 across the 16 of their papers we have counts for
20 papers
BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories
Fei Lin, Tengchao Zhang, Ziyang Gong +15
Self-Driving Chemical Laboratories (SDCLs) are moving chemical experimentation toward embodied automation, where machines must perceive laboratory scenes, reason about experimental…
SpatialBrain: Spatial Intelligence Growing from Experience
Yifan Zhou, Ziyang Gong, Xiaojun Ye +5
Spatial reasoning requires more than access to geometric tools: a reasoner must decide when direct observation is sufficient and when to reconstruct, measure, or change reference f…
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
Yifan Zhou, Qihao Yang, Yan Li +14
Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biological genomes. Current benc…
SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation
Xiaolong Zhou, Yifei Liu, Ziyang Gong +8
Multimodal Large Language Models (MLLMs) have made rapid progress in spatial intelligence, yet existing spatial reasoning benchmarks largely assume pristine visual inputs and overl…
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Yifan Yang, Ziyang Gong, Weiquan Huang +12
Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning optimizer for the skill, an…
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
Zisu Huang, Jingwen Xu, Yifan Yang +13
Language agents increasingly improve by reusing \emph{skills} -- structured procedural artifacts distilled from past experience. In particular, \emph{domain-level} and \emph{model-…
Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts
Wenhao Li, Daohai Yu, Gen Luo +7
Training Large Language Models (LLMs) on long contexts is severely constrained by prohibitive GPU memory overhead, not training time. The primary culprits are the activations, whos…
Compute Only Once: UG-Separation for Efficient Large Recommendation Models
Hui Lu, Zheng Chai, Shipeng Bai +15
Driven by scaling laws, recommender systems increasingly rely on larger-scale models to capture complex feature interactions and user behaviors, but this trend also leads to prohib…
MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critique
Gailun Zeng, Ziyang Luo, Hongzhan Lin +5
The ability of critique is vital for models to self-improve and serve as reliable AI assistants. While extensively studied in language-only settings, multimodal critique of Large M…
CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation
Shilei Cao, Ziyang Gong, Hehai Lin +10
In Remote Sensing (RS), Parameter-Efficient Fine-Tuning (PEFT) has emerged as a key approach to activate the generalizable representation ability of foundation models for downstrea…
ToxiEval-ZKP: A Structure-Private Verification Framework for Molecular Toxicity Repair Tasks
Fei Lin, Tengchao Zhang, Ziyang Gong +1
In recent years, generative artificial intelligence (GenAI) has demonstrated remarkable capabilities in high-stakes domains such as molecular science. However, challenges related t…
Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval
Wenhao Li, Yuxin Zhang, Gen Luo +4
Reducing the key-value (KV) cache burden in Large Language Models (LLMs) significantly accelerates inference. Dynamically selecting critical KV caches during decoding helps maintai…
Object Fidelity Diffusion for Remote Sensing Image Generation
Ziqi Ye, Shuran Ma, Jie Yang +5
High-precision controllable remote sensing image generation is both meaningful and challenging. Existing diffusion models often produce low-fidelity images due to their inability t…
Partial Weakly-Supervised Oriented Object Detection
Mingxin Liu, Peiyuan Zhang, Yuan Liu +8
The growing demand for oriented object detection (OOD) across various domains has driven significant research in this area. However, the high cost of dataset annotation remains a m…
Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?
Fei Lin, Ziyang Gong, Cong Wang +9
Toxicity remains a leading cause of early-stage drug development failure. Despite advances in molecular design and property prediction, the task of molecular toxicity repair, gener…
SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence
Ziyang Gong, Wenhao Li, Oliver Ma +7
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in various multimodal tasks. To pursue higher intelligence in space, MLLMs require integrating multiple s…
Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces
Gen Luo, Ganlin Yang, Ziyang Gong +15
The remarkable progress of Multimodal Large Language Models (MLLMs) has attracted increasing attention to extend them to physical entities like legged robot. This typically require…
Interleave-VLA: Enhancing Robot Manipulation with Interleaved Image-Text Instructions
Cunxin Fan, Xiaosong Jia, Yihang Sun +8
The rise of foundation models paves the way for generalist robot policies in the physical world. Existing methods relying on text-only instructions often struggle to generalize to…
Earth-Adapter: Bridge the Geospatial Domain Gaps with Mixture of Frequency Adaptation
Xiaoxing Hu, Ziyang Gong, Yupei Wang +8
Parameter-Efficient Fine-Tuning (PEFT) is a technique that allows us to adapt powerful Foundation Models (FMs) to diverse downstream tasks while preserving and unleashing their inh…
Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?
Yuru Jia, Valerio Marsocci, Ziyang Gong +3
Self-supervised learning (SSL) has revolutionized representation learning in Remote Sensing (RS), advancing Geospatial Foundation Models (GFMs) to leverage vast unlabeled satellite…