Related papers: Inference-Time Code Selection via Symbolic Equival…
LVLMs encounter significant challenges in image understanding and visual reasoning, leading to critical perception failures. Visual prompts, which incorporate image manipulation code, have shown promising potential in mitigating these…
Massively multilingual sentence representation models, e.g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks. However, the use of a large amount of data or inefficient model architectures results…
Existing LVLM-based reasoning segmentation methods often suffer from imprecise segmentation results and hallucinations in their text responses. This paper introduces POPEN, a novel framework designed to address these issues and achieve…
Standard metrics of performance of classifiers, such as accuracy and sensitivity, do not reveal the trust or confidence in the predicted labels of data. While other metrics such as the computed probability of a label or the signed distance…
Sentence encoders play a pivotal role in various NLP tasks; hence, an accurate evaluation of their compositional properties is paramount. However, existing evaluation methods predominantly focus on goal task-specific performance. This…
Symbolic quick error detection (SQED) has greatly improved efficiency in formal chip verification. However, it has a limitation in detecting single-instruction bugs due to its reliance on the self-consistency property. To address this, we…
Recent works in Task and Motion Planning (TAMP) show that training control policies on language-supervised robot trajectories with quality labeled data markedly improves agent task success rates. However, the scarcity of such data presents…
In supervised learning for medical image analysis, sample selection methodologies are fundamental to attain optimum system performance promptly and with minimal expert interactions (e.g. label querying in an active learning setup). In this…
Sample selection improves the efficiency and effectiveness of machine learning models by providing informative and representative samples. Typically, samples can be modeled as a sample graph, where nodes are samples and edges represent…
Recent advances in large language models have accelerated open-vocabulary EEG-to-imagined-text decoding, where non-invasive neural activity recorded during visual perception is translated into coherent natural language descriptions of…
In image restoration (IR), leveraging semantic priors from segmentation models has been a common approach to improve performance. The recent segment anything model (SAM) has emerged as a powerful tool for extracting advanced semantic priors…
Semi-supervised semantic segmentation aims to learn from a small amount of labeled data and plenty of unlabeled ones for the segmentation task. The most common approach is to generate pseudo-labels for unlabeled images to augment the…
Equivalent Representations (ERs) of code are textual representations that preserve the same semantics as the code itself, e.g., natural language comments and pseudocode. ERs play a critical role in software development and maintenance.…
The projector plays a crucial role in multi-modal language models (MLLMs). The number of visual tokens it outputs affects the efficiency of the MLLM, while the quality of the visual tokens influences the visual understanding capabilities of…
Test-time compute scaling has emerged as a powerful paradigm for enhancing mathematical reasoning in large language models (LLMs) by allocating additional computational resources during inference. However, current methods employ uniform…
Pre-trained segmentation models are a powerful and flexible tool for segmenting images. Recently, this trend has extended to medical imaging. Yet, often these methods only produce a single prediction for a given image, neglecting inherent…
Existing Large Language Models (LLMs) generate text through unidirectional autoregressive decoding methods to respond to various user queries. These methods tend to consider token selection in a simple sequential manner, making it easy to…
Repeated Sampling (RS) is a simple inference-time algorithm that has been shown to improve model performance on complex tasks. Although it is an effective way of scaling inference time, it often struggles to generate diverse solution…
We introduce SemCSE, an unsupervised method for learning semantic embeddings of scientific texts. Building on recent advances in contrastive learning for text embeddings, our approach leverages LLM-generated summaries of scientific…
Symbolic regression (SR) seeks closed-form mathematical expressions that fit observed data. Neural SR methods amortize the search by training an encoder to map observations directly to expressions in a single pass, but this amortized…