Related papers: Feedback Descent: Open-Ended Text Optimization via…
Recent advances in open-vocabulary object detection models will enable Automatic Target Recognition systems to be sustainable and repurposed by non-technical end-users for a variety of applications or missions. New, and potentially nuanced,…
Written language carries explicit and implicit biases that can distract from meaningful signals. For example, letters of reference may describe male and female candidates differently, or their writing style may indirectly reveal demographic…
We develop a modified online mirror descent framework that is suitable for building adaptive and parameter-free algorithms in unbounded domains. We leverage this technique to develop the first unconstrained online linear optimization…
The increasing availability of image-text pairs has largely fueled the rapid advancement in vision-language foundation models. However, the vast scale of these datasets inevitably introduces significant variability in data quality, which…
Nowadays, scene text recognition has attracted more and more attention due to its various applications. Most state-of-the-art methods adopt an encoder-decoder framework with attention mechanism, which generates text autoregressively from…
The recent development of online recommender systems has a focus on collaborative ranking from implicit feedback, such as user clicks and purchases. Different from explicit ratings, which reflect graded user preferences, the implicit…
Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. In particular, sophisticated neural network architectures are leveraged to capture the rich interactions between dialogue context and…
Aligning text-to-image diffusion model (T2I) with preference has been gaining increasing research attention. While prior works exist on directly optimizing T2I by preference data, these methods are developed under the bandit assumption of a…
Most Reading Comprehension methods limit themselves to queries which can be answered using a single sentence, paragraph, or document. Enabling models to combine disjoint pieces of textual evidence would extend the scope of machine…
Nowadays, an abundance of short text is being generated that uses nonstandard writing styles influenced by regional languages. Such informal and code-switched content are under-resourced in terms of labeled datasets and language models even…
Prompting has shown impressive success in enabling large pretrained language models (LMs) to perform diverse NLP tasks, especially when only few downstream data are available. Automatically finding the optimal prompt for each task, however,…
We study the $K$-armed contextual dueling bandit problem, a sequential decision making setting in which the learner uses contextual information to make two decisions, but only observes \emph{preference-based feedback} suggesting that one…
Many algorithms for the computation of correspondences between deformable shapes rely on some variant of nearest neighbor matching in a descriptor space. Such are, for example, various point-wise correspondence recovery algorithms used as a…
Optimization with preference feedback is an active research area with many applications in engineering systems where humans play a central role, such as building control and autonomous vehicles. While most existing studies focus on…
Preference-based reward learning is widely used for shaping agent behavior to match a user's preference, yet its sparse binary feedback makes it especially vulnerable to causal confusion. The learned reward often latches onto spurious…
Embedding-based similarity metrics between text sequences can be influenced not just by the content dimensions we most care about, but can also be biased by spurious attributes like the text's source or language. These document confounders…
In a number of information retrieval applications (e.g., patent search, literature review, due diligence, etc.), preventing false negatives is more important than preventing false positives. However, approaches designed to reduce review…
Decision-making problems are commonly formulated as optimization problems, which are then solved to make optimal decisions. In this work, we consider the inverse problem where we use prior decision data to uncover the underlying…
Preference-based reinforcement learning (PBRL) offers a promising alternative to explicit reward engineering by learning from pairwise trajectory comparisons. However, real-world preference data often comes from heterogeneous annotators…
Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While…