Search Results for author:
Found 6 papers, 2 papers with code
TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models
We conduct extensive experiments on both general and document-oriented MLLM benchmarks, and show that TextHawk outperforms the state-of-the-art methods, demonstrating its effectiveness and superiority in fine-grained document perception and general abilities.
Android in the Zoo: Chain-of-Action-Thought for GUI Agents
To address this, this work presents Chain-of-Action-Thought (dubbed CoAT), which takes the description of the previous actions, the current screen, and more importantly the action thinking of what actions should be performed and the outcomes led by the chosen action.
Temporal-Spatial Entropy Balancing for Causal Continuous Treatment-Effect Estimation
However, temporal and spatial dimensions are extremely critical in the logistics field, and this limitation may directly affect the precision of subsidy and pricing strategies.
DocStormer: Revitalizing Multi-Degraded Colored Document Images to Pristine PDF
Thus, we propose DocStormer, a novel algorithm designed to restore multi-degraded colored documents to their potential pristine PDF.
Efficient Image Captioning for Edge Devices
On the other hand, we transfer the image-text retrieval design of CLIP to image captioning scenarios by devising a novel visual concept extractor and a cross-modal modulator.
Controllable Image Captioning via Prompting
Despite the remarkable progress of image captioning, existing captioners typically lack the controllable capability to generate desired image captions, e. g., describing the image in a rough or detailed manner, in a factual or emotional view, etc.
