InstAP introduces instance-aware pre-training with a new dual-granularity dataset InstVL that improves both fine-grained instance retrieval and global video understanding over standard VLP baselines.
Multi- grained vision language pre-training: Align- ing texts with visual concepts
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
representative citing papers
Stitch-a-Demo is a retrieval-based method that assembles visually coherent video demonstrations from multistep textual descriptions by training on weakly supervised procedural data with hard negatives.
CompART adds a composition loss on decomposed captions to regularize attention sums and improves multi-object grounding plus VQA across four VLM types and six benchmarks.
ViperGPT generates executable Python code to compose pre-trained vision-and-language modules into programs that answer visual queries, reaching state-of-the-art results with no additional training.
Qwen-RobotWorld is a language-conditioned video world model using Double-Stream MMDiT, an 8.6M-frame embodied corpus, and progressive curriculum training that ranks first on EWMBench and DreamGen Bench.
T-CLIP introduces a physics-aware thermal captioning dataset (IR-Cap) and a decoupled dual-LoRA adaptation of CLIP that improves cross-modal retrieval on thermal benchmarks by separating scene-level and object-level thermal understanding.
WikiCLIP reaches 28.5% OVEN-unseen accuracy (vs 24.5% AutoVER) at 14.5 ms latency by vision-guided LLM embeddings plus hard-negative text swaps.
LURE reduces object hallucination in LVLMs by 23% via post-hoc revision informed by co-occurrence, uncertainty, and text position analysis.
GeoFuse fuses aligned road maps with satellite imagery via token/channel interactions and dynamic gating plus contrastive learning, lifting Recall@1 by 3.46% on University-1652 and 23.18% on DenseUAV under weather degradation.
citing papers explorer
-
InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding
InstAP introduces instance-aware pre-training with a new dual-granularity dataset InstVL that improves both fine-grained instance retrieval and global video understanding over standard VLP baselines.
-
Stitch-a-Demo: Video Demonstrations from Multistep Descriptions
Stitch-a-Demo is a retrieval-based method that assembles visually coherent video demonstrations from multistep textual descriptions by training on weakly supervised procedural data with hard negatives.
-
The ART of Composition: Attention-Regularized Training for Compositional Visual Grounding
CompART adds a composition loss on decomposed captions to regularize attention sums and improves multi-object grounding plus VQA across four VLM types and six benchmarks.
-
ViperGPT: Visual Inference via Python Execution for Reasoning
ViperGPT generates executable Python code to compose pre-trained vision-and-language modules into programs that answer visual queries, reaching state-of-the-art results with no additional training.
-
Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation
Qwen-RobotWorld is a language-conditioned video world model using Double-Stream MMDiT, an 8.6M-frame embodied corpus, and progressive curriculum training that ranks first on EWMBench and DreamGen Bench.
-
T-CLIP: Enabling Thermal Perception for Contrastive Language-Image Pretraining
T-CLIP introduces a physics-aware thermal captioning dataset (IR-Cap) and a decoupled dual-LoRA adaptation of CLIP that improves cross-modal retrieval on thermal benchmarks by separating scene-level and object-level thermal understanding.
-
WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition
WikiCLIP reaches 28.5% OVEN-unseen accuracy (vs 24.5% AutoVER) at 14.5 ms latency by vision-guided LLM embeddings plus hard-negative text swaps.
-
Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
LURE reduces object hallucination in LVLMs by 23% via post-hoc revision informed by co-occurrence, uncertainty, and text position analysis.
-
Road Maps as Free Geometric Priors: Weather-Invariant Drone Geo-Localization with GeoFuse
GeoFuse fuses aligned road maps with satellite imagery via token/channel interactions and dynamic gating plus contrastive learning, lifting Recall@1 by 3.46% on University-1652 and 23.18% on DenseUAV under weather degradation.