4 citations · 9 across the 11 of their papers we have counts for
12 papers
Skill Training with Corruption and Reconstruction Loop
Mo Li, Zixin Yin, Ting Cao +3
Large Language Models (LLMs) often struggle in highly specialized domains. Rather than parameter-level adaptation of LLMs which is costly and difficult to interpret, external skill…
GatedLinear: Adaptive Routing of Complementary Linear Bases for Time Series Forecasting
Qitai Tan, Ruiwen Gu, Yilin Su +3
Time series forecasting requires models to capture diverse, often mutually exclusive, temporal dynamics, from smooth trend continuation to nonstationary drift and strict phase-alig…
ATOD: Annealed Turn-Aware On-Policy Distillation for Multi-Turn Agentic Tasks
Qitai Tan, Zefang Zong, Mo Li +3
Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement. On-policy distillation (OPD) provides dense teac…
Learning from Execution: Self-Evolving Memory for Private-Library Code Generation
Mofei Li, Taozhi Chen, Guowei Yang +1
Large Language Models (LLMs) have achieved strong performance on general code generation, but their effectiveness drops sharply in enterprise settings where software development re…
Learning to Commit: Generating Organic Pull Requests via Online Repository Memory
Mo Li, L. H. Xu, Qitai Tan +2
Large language model (LLM)-based coding agents achieve impressive results on controlled benchmarks yet routinely produce pull requests that real maintainers reject. The root cause…
Kimi K2.5: Visual Agentic Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +333
We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that…
SynTSBench: Rethinking Temporal Pattern Learning in Deep Learning Models for Time Series
Qitai Tan, Yiyun Chen, Mo Li +3
Recent advances in deep learning have driven rapid progress in time series forecasting, yet many state-of-the-art models continue to struggle with robust performance in real-world…
Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management
Mo Li, L. H. Xu, Qitai Tan +3
Large Language Models (LLMs) suffer from significant performance degradation when processing long contexts due to proactive interference, where irrelevant information in earlier pa…
MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence
Sihan Yang, Runsen Xu, Yiman Xie +10
Spatial intelligence is essential for multimodal large language models (MLLMs) operating in the complex physical world. Existing benchmarks, however, probe only single-image relati…
Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement
Maosong Cao, Taolin Zhang, Mo Li +5
The quality of Supervised Fine-Tuning (SFT) data plays a critical role in enhancing the conversational capabilities of Large Language Models (LLMs). However, as LLMs become more ad…
NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities
Mo Li, Songyang Zhang, Taolin Zhang +3
The capability of large language models to handle long-context information is crucial across various real-world applications. Existing evaluation methods often rely either on real-…
VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models
Haodong Duan, Xinyu Fang, Junming Yang +41
We present VLMEvalKit: an open-source toolkit for evaluating large multi-modality models based on PyTorch. The toolkit aims to provide a user-friendly and comprehensive framework f…