5 papers
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
MiroMind Team, Song Bai, Lidong Bing +52
We present MiroThinker v1.0, an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike previous agents that only scale…
AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs
Chengming Cui, Tianxin Wei, Ziyi Chen +6
Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding behaviors. Inference-time ensembling pr…
Learnable Query Aggregation with KV Routing for Cross-view Geo-localisation
Hualin Ye, Bingxi Liu, Jixiang Du +3
Cross-view geo-localisation (CVGL) aims to estimate the geographic location of a query image by matching it with images from a large-scale database. However, the significant view-p…
Cascade Speculative Drafting for Even Faster LLM Inference
Ziyi Chen, Xiaocong Yang, Jiacheng Lin +3
Introduced to enhance the efficiency of large language model (LLM) inference, speculative decoding operates by having a smaller model generate a draft. A larger target model then r…
V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding
Junqi Ge, Ziyi Chen, Jintao Lin +4
Vision-Language Models (VLMs) have shown promising capabilities in handling various multimodal tasks, yet they struggle in long-context scenarios, particularly in tasks involving v…