Search Results for author:
Found 22 papers, 6 papers with code
Discriminator-Guided Multi-step Reasoning with Language Models
In the context of multi-step reasoning, language models (LMs) probabilities are often miscalibrated -- solutions with high probabilities are not always correct.
Unsupervised Task Graph Generation from Instructional Video Transcripts
This work explores the problem of generating task graphs of real-world activities.
Multimodal Subtask Graph Generation from Instructional Videos
Real-world tasks consist of multiple inter-dependent subtasks (e. g., a dirty pan needs to be washed before it can be used for cooking).
Exploring the Benefits of Training Expert Language Models over Instruction Tuning
Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks.
Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers
Since the recent advent of regulations for data protection (e. g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sensitive data in pre-trained models without retraining from scratch.
Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching
Despite surprising performance on zero-shot transfer, pre-training a large-scale multimodal model is often prohibitive as it requires a huge amount of data and computing resources.
Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost
The forward and backward cost are thus linear to the number of edges, which each attention head can also choose flexibly based on the input.
Knowledge Unlearning for Mitigating Privacy Risks in Language Models
Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities.
Grouping-matrix based Graph Pooling with Adaptive Number of Clusters
Conventional methods ask users to specify an appropriate number of clusters as a hyperparameter, then assume that all input graphs share the same number of clusters.
Pure Transformers are Powerful Graph Learners
We show that standard Transformers without graph-specific modifications can lead to promising results in graph learning both in theory and practice.
Ranked #7 on
Graph Regression
on PCQM4Mv2-LSC
Towards More Objective Evaluation of Class Incremental Learning: Representation Learning Perspective
While the common method for evaluating CIL algorithms is based on average test accuracy for all learned classes, we argue that maximizing accuracy alone does not necessarily lead to effective CIL algorithms.
Few-shot Subgoal Planning with Language Models
Pre-trained large language models have shown successful progress in many language understanding benchmarks.
Few-shot Reranking for Multi-hop QA via Language Model Prompting
To alleviate the need for a large number of labeled question-document pairs for retriever training, we propose PromptRank, which relies on large language models prompting for multi-hop path reranking.
Rebalancing Batch Normalization for Exemplar-based Class-Incremental Learning
The main reason for the ineffectiveness of their method lies in not fully addressing the data imbalance issue, especially in computing the gradients for learning the affine transformation parameters of BN.
On-the-Fly Rectification for Robust Large-Vocabulary Topic Inference
Across many data domains, co-occurrence statistics about the joint appearance of objects are powerfully informative.
Practical Correlated Topic Modeling and Analysis via the Rectified Anchor Word Algorithm
Despite great scalability on large data and their ability to understand correlations between topics, spectral topic models have not been widely used due to the absence of reliability in real data and lack of practical implementations.
Prior-aware Dual Decomposition: Document-specific Topic Inference for Spectral Topic Models
Spectral topic modeling algorithms operate on matrices/tensors of word co-occurrence statistics to learn topic-specific word distributions.
Low-dimensional Embeddings for Interpretable Anchor-based Topic Inference
The anchor words algorithm performs provably efficient topic model inference by finding an approximate convex hull in a high-dimensional word co-occurrence space.
Robust Spectral Inference for Joint Stochastic Matrix Factorization
Spectral inference provides fast algorithms and provable optimality for latent topic analysis.
Beyond Exchangeability: The Chinese Voting Process
Many online communities present user-contributed responses such as reviews of products and answers to questions.
Basic Reasoning with Tensor Product Representations
In this paper we present the initial development of a general theory for mapping inference in predicate logic to computation over Tensor Product Representations (TPRs; Smolensky (1990), Smolensky & Legendre (2006)).
Reasoning in Vector Space: An Exploratory Study of Question Answering
Question answering tasks have shown remarkable progress with distributed vector representation.
