OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Codeby Maxence…
Benchmarking the Performance of Pre-trained LLMs across Urdu NLP Tasksby Munief Hassan Tahir, Sana Shams,…
Less is more: Summarizing Patch Tokens for efficient Multi-Label Class-Incremental Learningby Thomas De Min, Massimiliano…
Randomized heuristic repair for large-scale multidimensional knapsack problemby Jean P. MartinsFirst submitted to arxiv on:…
GECKO: Generative Language Model for English, Code and Koreanby Sungwoo Oh, Donggyu KimFirst submitted to…
Exposing Image Classifier Shortcuts with Counterfactual Frequency (CoF) Tablesby James Hinns, David MartensFirst submitted to…
CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentationby Zhuoyan Luo, Yinghao Wu,…
Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMsby Sreyan Ghosh, Chandra Kiran Reddy…
InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generationby Yuchi Wang, Junliang Guo, Jianhong Bai,…
Prompt-Aware Adapter: Towards Learning Adaptive Visual Tokens for Multimodal Large Language Modelsby Yue Zhang, Hehe…