Stitching Gaps: Fusing Situated Perceptual Knowledge with Vision Transformers for High-Level Image Classificationby Delfina Sol…
OpenMedLM: Prompt engineering can out-perform fine-tuning in medical question-answering with open-source large language modelsby Jenish…
On the Scaling Laws of Geographical Representation in Language Modelsby Nathan Godey, Éric de la…
Leveraging AI Predicted and Expert Revised Annotations in Interactive Segmentation: Continual Tuning or Full Training?by…
Functional Benchmarks for Robust Evaluation of Reasoning Performance, and the Reasoning Gapby Saurabh Srivastava, Annarose…
Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Modelsby Chen Qian, Jie Zhang,…
TV-TREES: Multimodal Entailment Trees for Neuro-Symbolic Video Reasoningby Kate Sanders, Nathaniel Weir, Benjamin Van DurmeFirst…
Loose LIPS Sink Ships: Asking Questions in Battleship with Language-Informed Program Samplingby Gabriel Grand, Valerio…
EROS: Entity-Driven Controlled Policy Document Summarizationby Joykirat Singh, Sehban Fazili, Rohan Jain, Md Shad AkhtarFirst…
Resonance RoPE: Improving Context Length Generalization of Large Language Modelsby Suyuchen Wang, Ivan Kobyzev, Peng…