38 accepted papers
The central challenge in multimodal generative modeling lies in accurately approximating the joint data distribution, even when some modalities are missing. Existing multimodal VAEs solve this by designing increasingly complex encoding architectures, relying on modality-specific encoders, factorized
Sets represent a fundamental abstraction across many types of data. To handle the unordered nature of set-structured data, models such as DeepSets and PointNet rely on fixed, non-learnable pooling operations (e.g., sum or max) -- a design choice that can hinder the transferability of learned embeddi…
Planning in open-world environments, where agents must act with partially observed states and incomplete knowledge, is a central challenge in embodied AI. Open-world planning involves not only sequencing actions but also determining what information the agent needs to sense to enable those actions.…
Linear Predictive Clustering (LPC) partitions samples based on shared linear relationships between feature and target variables, with numerous applications including marketing, medicine, and education. Greedy optimization methods, commonly used for LPC, alternate between clustering and linear regres
We study the neural program synthesis of $\textit{parameterized}$ function families through the lens of meta-learning with hypernetworks. Given a user intent $U$, a meta-learner $M_{\phi}$ produces a full weight set $\hat{\theta}=M_{\phi}(U)$ for a target neural network with fixed architecture $S$,…
The ability to actively acquire information is essential for open-world planning under partial observability and incomplete knowledge. However, most existing embodied AI systems either assume a known object category or rely on passive perception strategies that exhaustively gather object and relatio…
LLM query-passage relevance assessment is typically studied using a one-by-one pointwise (PW) strategy where each LLM call judges one passage at a time. However, this strategy requires as many LLM calls as there are passages while also preventing information sharing between passages. We thus hypothe
Finding high-quality representations of heterogeneous tabular datasets is crucial for their effective use in downstream machine learning tasks. Contrastive representation learning (CRL) methods have been previously shown to provide a straightforward way to learn such representations across various d…
Large language models (LLM) are being increasingly applied to tasks requiring commonsense reasoning. Despite their outstanding potential, the reasoning process of LLMs is prone to errors and hallucinations that hinder their applicability, especially in high-stakes scenarios. Several works have attem…
Dense Passage Retrieval (DPR) typically relies on Euclidean or cosine distance to measure query–passage relevance in embedding space, which is effective when embeddings lie on a linear manifold. However, our experiments across DPR benchmarks suggest that embeddings often lie on lower-dimensional, no
Despite significant recent advances in the field of Deep Reinforcement Learning (DRL), such methods typically incur high cost of training to learn effective policies, thus posing cost and safety challenges in many practical applications. To improve the learning efficiency of (D)RL methods, transfer…
Open-world planning with incomplete knowledge is crucial for real-world embodied AI tasks. Despite that, existing LLM-based planners struggle with long chains of sequential reasoning, while symbolic planners face combinatorial explosion of states and actions for complex domains due to reliance on gr…
Query-driven recommendation with unknown items poses a challenge for users to understand why certain items are appropriate for their needs. Query-driven Contrastive Summarization (QCS) is a methodology designed to address this issue by leveraging language-based item descriptions to clarify contrasts…
Offline reinforcement learning (RL) is crucial when online exploration is costly or unsafe but often struggles with high epistemic uncertainty due to limited data. Existing methods rely on fixed conservative policies, restricting adaptivity and generalization. To address this, we propose Reflect-the…
We present a Transformer-based framework for Constraint Satisfaction Problems (CSPs). CSPs find use in many applications and thus accelerating their solution with machine learning is of wide interest. Most existing approaches rely on supervised learning from feasible solutions or reinforcement lear…
Knowledge Graphs (KGs) provide a widely used format for representing entities and their relationships and have found use in diverse applications including question answering and recommendation. A majority of current research on KG inference has focused on reasoning with atomic facts (triples) and h…
In multi-objective text generation, we aim to optimize over multiple weighted aspects (e.g., toxicity, semantic preservation, fluency) of the generated text. However, multi-objective weighting schemes may change dynamically in practice according to deployment requirements, evolving business needs, p…
Knowledge Graph Question Answering (KGQA) methods seek to answer Natural Language questions using the relational information stored in Knowledge Graphs (KGs). With the recent advancements of Large Language Models (LLMs) and their remarkable reasoning abilities, there is a growing trend to leverage t…
Recent advances in Large Language Models (LLM) have led to substantial interest in their application to commonsense reasoning tasks. Despite their potential, LLMs are susceptible to reasoning errors and hallucinations that may be harmful in use cases where accurate reasoning is critical. This challe…
Offensive and toxic text on social media platforms can lead to polarization and divisiveness within online communities and hinders constructive dialogue. Text detoxification is a crucial task in natural language processing to ensure the generation of non-toxic and safe text. Text detoxification is a…
Offline reinforcement learning (RL) addresses the problem of learning a performant policy from a fixed batch of data collected by following some behavior policy. Model-based approaches are particularly appealing in the offline setting since they can extract more learning signals from the logged data…
Text detoxification is a conditional text generation task aiming to remove offensive content from toxic text. It is highly useful for online forums and social media, where offensive content is frequently encountered. Intuitively, there are diverse ways to detoxify sentences while preserving their me…
The Abstraction and Reasoning Corpus (ARC) aims at benchmarking the performance of general artificial intelligence algorithms. The ARC's focus on broad generalization and few-shot learning has made it difficult to solve using pure machine learning. A more promising approach has been to perform progr…
The k-center clustering algorithm, introduced over 35 years ago, is known to be robust to class imbalance prevalent in many clustering problems and has various applications such as data summarization, document clustering, and facility location determination. Unfortunately, existing k-center algorith…
In this paper, we model aspects of communication beyond the words that are said. Specifically, we aim to detect interruptions and active listening events, which are important elements in any dialogue. We build a dataset with fine-grained annotations for each category and train multimodal models that…
Recent advances in efficient planning in deterministic or stochastic high-dimensional domains with continuous action spaces leverage backpropagation through a model of the environment to directly optimize action sequences. However, existing methods typically do not take risk into account when optimi…
Predictive models are traditionally optimized independently of their use in downstream decision-based optimization. The ‘smart, predict then optimize’ (SPO) framework addresses this shortcoming by optimizing predictive models in order to
Text-based games present a unique class of sequential decision making problem in which agents interact with a partially observable, simulated environment via actions and observations conveyed through natural language. Such observations typically include instructions that, in a reinforcement learning…
Recent advances in deep learning have enabled optimization of deep reactive policies (DRPs) for continuous MDP planning by encoding a parametric policy as a deep neural network and exploiting automatic differentiation in an end-to-end model-based gradient descent framework. This approach has proven…
Learning from Demonstrations (LfD) is a powerful approach for incorporating advice from experts in the form of demonstrations. However, demonstrations often come from multiple sub-optimal experts with conflicting goals, rendering them difficult to incorporate effectively in online settings. To addre…
In reinforcement learning, agents that consider the context or current state when transferring source policies have been shown to outperform context-free approaches. However, existing approaches suffer from limitations, including sensitivity to sparse or delayed rewards and estimation errors in valu…
As image-based deep learning becomes pervasive on every device, from cell phones to smart watches, there is a growing need to develop methods that continually learn from data while minimizing memory footprint and power consumption. While memory replay techniques have shown exceptional promise for th…
Explaining the influence of training data on deep neural network predictions is a critical tool for debugging models through data curation. A recent tractable and appealing approach for this task was provided via the concept of Representer Point Selection (RPS), i.e. a method the leverages the dual…
Sample efficiency and risk-awareness are central to the development of practical reinforcement learning (RL) for complex decision-making. The former can be addressed by transfer learning, while the latter by optimizing some utility function of the return. However, the problem of transferring skills…
Recent advances in symbolic dynamic programming (SDP) have significantly broadened the class of MDPs for which exact closed-form value functions can be derived. However, no existing solution methods can solve complex discrete and continuous state MDPs where a linear program determines state transiti…
Resolving the exploration-exploitation trade-off remains a fundamental problem in the design and implementation of reinforcement learning (RL) algorithms. In this paper, we focus on model-free RL using the epsilon-greedy exploration policy, which despite its simplicity, remains one of the most frequ…
Potential based reward shaping is a powerful technique for accelerating convergence of reinforcement learning algorithms. Typically, such information includes an estimate of the optimal value function and is often provided by a human expert or other sources of domain knowledge. However, this informa…
Given recent deep learning results that demonstrate the ability to effectively optimize high-dimensional non-convex functions with gradient descent optimization on GPUs, we ask in this paper whether symbolic gradient optimization tools such as Tensorflow can be effective for planning in hybrid (mixe…