7 papers
Multimodal Latent Reasoning via Hierarchical Visual Cues Injection
Yiming Zhang, Qiangyu Yan, Borui Jiang +1
The advancement of multimodal large language models (MLLMs) has enabled impressive perception capabilities. However, their reasoning process often remains a "fast thinking" paradig…
GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics
Modi Jin, Yiming Zhang, Boyuan Sun +3
This paper presents GeoAgent, a model capable of reasoning closely with humans and deriving fine-grained address conclusions. Previous RL-based methods have achieved breakthroughs…
Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds
Fan Wang, Pengtao Shao, Yiming Zhang +6
In-Context Reinforcement Learning (ICRL) enables agents to learn automatically and on-the-fly from their interactive experiences. However, a major challenge in scaling up ICRL is t…
Multi-Scale Finetuning for Encoder-based Time Series Foundation Models
Zhongzheng Qiao, Chenghao Liu, Yiming Zhang +6
Time series foundation models (TSFMs) demonstrate impressive zero-shot performance for time series forecasting. However, an important yet underexplored challenge is how to effectiv…
CIE: Controlling Language Model Text Generations Using Continuous Signals
Vinay Samuel, Harshita Diddee, Yiming Zhang +1
Aligning language models (LMs) with user intent is becoming increasingly relevant to enhance user experience. This calls for designing methods that can allow users to control the p…
NoveltyBench: Evaluating Language Models for Humanlike Diversity
Yiming Zhang, Harshita Diddee, Susan Holm +5
Language models have demonstrated remarkable capabilities on standard benchmarks, yet they struggle increasingly from mode collapse, the inability to generate diverse and novel out…