Virginia R. de Sa

Vijay Veerabadran, Srinivas Ravishankar, Yuan Tang et al.

Humans solving algorithmic (or) reasoning problems typically exhibit solution times that grow as a function of problem difficulty. Adaptive recurrent neural networks have been shown to exhibit this property for various language-processing tasks. However, little work has been performed to assess whether such adaptive computation can also enable vision models to extrapolate solutions beyond their training distribution's difficulty level, with prior work focusing on very simple tasks. In this study, we investigate a critical functional role of such adaptive processing using recurrent neural networks: to dynamically scale computational resources conditional on input requirements that allow for zero-shot generalization to novel difficulty levels not seen during training using two challenging visual reasoning tasks: PathFinder and Mazes. We combine convolutional recurrent neural networks (ConvRNNs) with a learnable halting mechanism based on Graves (2016). We explore various implementations of such adaptive ConvRNNs (AdRNNs) ranging from tying weights across layers to more sophisticated biologically inspired recurrent networks that possess lateral connections and gating. We show that 1) AdRNNs learn to dynamically halt processing early (or late) to solve easier (or harder) problems, 2) these RNNs zero-shot generalize to more difficult problem settings not shown during training by dynamically increasing the number of recurrent iterations at test time. Our study provides modeling evidence supporting the hypothesis that recurrent processing enables the functional advantage of adaptively allocating compute resources conditional on input requirements and hence allowing generalization to harder difficulty levels of a visual reasoning problem without training.

Shuangquan Feng, Laura Fleig, Ruisen Tu et al.

Large language models (LLMs) enable increasingly capable tutoring-style conversational agents, yet effective tutoring requires sensitivity to learners' affective and cognitive states beyond text alone. Facial expressions provide immediate and practical cues of confusion, frustration, or engagement, but remain underexplored in LLM-driven tutoring. We investigate whether facial-expression-aware signals can improve empathetic tutoring responses through prompt-level integration, without end-to-end retraining. We build a scalable simulated tutoring environment where a student agent exhibits diverse facial behaviors from a large unlabeled facial expression video dataset, and compare four tutor variants: a text-only LLM baseline, a multimodal baseline using a random facial frame, and two Action Unit estimation model (AUM)-based methods that either inject textual AU descriptions or select a peak-expression frame for visual grounding. Across 960 multi-turn conversations spanning three tutor backbones (GPT-5.1, Claude Ops 4.5, and Gemini 2.5 Pro), we evaluate targeted pairwise comparisons with five human raters and an exhaustive AI evaluator. AU-based conditioning consistently improves empathetic responsiveness to facial expressions across all tutor backbones, while AUM-guided peak-frame selection outperforms random-frame visual input. Textual AU abstraction and peak-frame visual injection show model-dependent advantages. Control analyses show that this improvement does not come at the expense of worse pedagogical clarity or responsiveness to textual cues. Finally, AI-human agreement is highest on facial-expression-grounded empathy, supporting scalable AI evaluation for this dimension. Overall, our results show that lightweight, structured facial expression representations can meaningfully enhance empathy in LLM-based tutoring systems with minimal overhead.

Shuangquan Feng, Junhua Ma, Virginia R. de Sa

Researchers have proposed to use data of human preference feedback to fine-tune text-to-image generative models. However, the scalability of human feedback collection has been limited by its reliance on manual annotation. Therefore, we develop and test a method to automatically score user preferences from their spontaneous facial expression reaction to the generated images. We collect a dataset of Facial Expression Reaction to Generated Images (FERGI) and show that the activations of multiple facial action units (AUs) are highly correlated with user evaluations of the generated images. We develop an FAU-Net (Facial Action Units Neural Network), which receives inputs from an AU estimation model, to automatically score user preferences for text-to-image generation based on their facial expression reactions, which is complementary to the pre-trained scoring models based on the input text prompts and generated images. Integrating our FAU-Net valence score with the pre-trained scoring models improves their consistency with human preferences. This method of automatic annotation with facial expression analysis can be potentially generalized to other generation tasks. The code is available at https://github.com/ShuangquanFeng/FERGI, and the dataset is also available at the same link for research purposes.

Shuangquan Feng, Virginia R. de Sa

Automatic facial action unit (AU) recognition is used widely in facial expression analysis. Most existing AU recognition systems aim for cross-participant non-calibrated generalization (NCG) to unseen faces without further calibration. However, due to the diversity of facial attributes across different identities, accurately inferring AU activation from single images of an unseen face is sometimes infeasible, even for human experts -- it is crucial to first understand how the face appears in its neutral expression, or significant bias may be incurred. Therefore, we propose to perform one-frame calibration (OFC) in AU recognition: for each face, a single image of its neutral expression is used as the reference image for calibration. With this strategy, we develop a Calibrating Siamese Network (CSN) for AU recognition and demonstrate its remarkable effectiveness with a simple iResNet-50 (IR50) backbone. On the DISFA, DISFA+, and UNBC-McMaster datasets, we show that our OFC CSN-IR50 model (a) substantially improves the performance of IR50 by mitigating facial attribute biases (including biases due to wrinkles, eyebrow positions, facial hair, etc.), (b) substantially outperforms the naive OFC method of baseline subtraction as well as (c) a fine-tuned version of this naive OFC method, and (d) also outperforms state-of-the-art NCG models for both AU intensity estimation and AU detection.

Vijay Veerabadran, Virginia R. de Sa

Work at the intersection of vision science and deep learning is starting to explore the efficacy of deep convolutional networks (DCNs) and recurrent networks in solving perceptual grouping problems that underlie primate visual recognition and segmentation. Here, we extend this line of work to investigate the compactness and generalizability of DCN solutions to learning low-level perceptual grouping routines involving contour integration. We introduce V1Net, a bio-inspired recurrent unit that incorporates lateral connections ubiquitous in cortical circuitry. Feedforward convolutional layers in DCNs can be substituted with V1Net modules to enhance their contextual visual processing support for perceptual grouping. We compare the learning efficiency and accuracy of V1Net-DCNs to that of 14 carefully selected feedforward and recurrent neural architectures (including state-of-the-art DCNs) on MarkedLong -- a synthetic forced-choice contour integration dataset of 800,000 images we introduce here -- and the previously published Pathfinder contour integration benchmarks. We gauged solution generalizability by measuring the transfer learning performance of our candidate models trained on MarkedLong that were fine-tuned to learn PathFinder. Our results demonstrate that a compact 3-layer V1Net-DCN matches or outperforms the test accuracy and sample efficiency of all tested comparison models which contain between 5x and 1000x more trainable parameters; we also note that V1Net-DCN learns the most compact generalizable solution to MarkedLong. A visualization of the temporal dynamics of a V1Net-DCN elucidates its usage of interpretable grouping computations to solve MarkedLong. The compact and rich representations of V1Net-DCN also make it a promising candidate to build on-device machine vision algorithms as well as help better understand biological cortical circuitry.

Shuai Tang, Virginia R. de Sa

The large amount of online data and vast array of computing resources enable current researchers in both industry and academia to employ the power of deep learning with neural networks. While deep models trained with massive amounts of data demonstrate promising generalisation ability on unseen data from relevant domains, the computational cost of finetuning gradually becomes a bottleneck in transfering the learning to new domains. We address this issue by leveraging the low-rank property of learnt feature vectors produced from deep neural networks (DNNs) with the closed-form solution provided in kernel ridge regression (KRR). This frees transfer learning from finetuning and replaces it with an ensemble of linear systems with many fewer hyperparameters. Our method is successful on supervised and semi-supervised transfer learning tasks.

Shuai Tang, Mahta Mousavi, Virginia R. de Sa

Word embeddings learnt from large corpora have been adopted in various applications in natural language processing and served as the general input representations to learning systems. Recently, a series of post-processing methods have been proposed to boost the performance of word embeddings on similarity comparison and analogy retrieval tasks, and some have been adapted to compose sentence representations. The general hypothesis behind these methods is that by enforcing the embedding space to be more isotropic, the similarity between words can be better expressed. We view these methods as an approach to shrink the covariance/gram matrix, which is estimated by learning word vectors, towards a scaled identity matrix. By optimising an objective in the semi-Riemannian manifold with Centralised Kernel Alignment (CKA), we are able to search for the optimal shrinkage parameter, and provide a post-processing method to smooth the spectrum of learnt word vectors which yields improved performance on downstream tasks.

Shuai Tang, Paul Smolensky, Virginia R. de Sa

idely used recurrent units, including Long-short Term Memory (LSTM) and the Gated Recurrent Unit (GRU), perform well on natural language tasks, but their ability to learn structured representations is still questionable. Exploiting reduced Tensor Product Representations (TPRs) --- distributed representations of symbolic structure in which vector-embedded symbols are bound to vector-embedded structural positions --- we propose the TPRU, a simple recurrent unit that, at each time step, explicitly executes structural-role binding and unbinding operations to incorporate structural information into learning. A gradient analysis of our proposed TPRU is conducted to support our model design, and its performance on multiple datasets shows the effectiveness of our design choices. Furthermore, observations on a linguistically grounded study demonstrate the interpretability of our TPRU.

Shuai Tang, Virginia R. de Sa

Consensus maximisation learning can provide self-supervision when different views are available of the same data. The distributional hypothesis provides another form of useful self-supervision from adjacent sentences which are plentiful in large unlabelled corpora. Motivated by the observation that different learning architectures tend to emphasise different aspects of sentence meaning, we present a new self-supervised learning framework for learning sentence representations which minimises the disagreement between two views of the same sentence where one view encodes the sentence with a recurrent neural network (RNN), and the other view encodes the same sentence with a simple linear model. After learning, the individual views (networks) result in higher quality sentence representations than their single-view learnt counterparts (learnt using only the distributional hypothesis) as judged by performance on standard downstream tasks. An ensemble of both views provides even better generalisation on both supervised and unsupervised downstream tasks. Also, importantly the ensemble of views trained with consensus maximisation between the two different architectures performs better on downstream tasks than an analogous ensemble made from the single-view trained counterparts.

Shuai Tang, Virginia R. de Sa

The encoder-decoder models for unsupervised sentence representation learning tend to discard the decoder after being trained on a large unlabelled corpus, since only the encoder is needed to map the input sentence into a vector representation. However, parameters learnt in the decoder also contain useful information about language. In order to utilise the decoder after learning, we present two types of decoding functions whose inverse can be easily derived without expensive inverse calculation. Therefore, the inverse of the decoding function serves as another encoder that produces sentence representations. We show that, with careful design of the decoding functions, the model learns good sentence representations, and the ensemble of the representations produced from the encoder and the inverse of the decoder demonstrate even better generalisation ability and solid transferability.

Shuai Tang, Virginia R. de Sa

Multi-view learning can provide self-supervision when different views are available of the same data. The distributional hypothesis provides another form of useful self-supervision from adjacent sentences which are plentiful in large unlabelled corpora. Motivated by the asymmetry in the two hemispheres of the human brain as well as the observation that different learning architectures tend to emphasise different aspects of sentence meaning, we create a unified multi-view sentence representation learning framework, in which, one view encodes the input sentence with a Recurrent Neural Network (RNN), and the other view encodes it with a simple linear model, and the training objective is to maximise the agreement specified by the adjacent context information between two views. We show that, after training, the vectors produced from our multi-view training provide improved representations over the single-view training, and the combination of different views gives further representational improvement and demonstrates solid transferability on standard downstream tasks.

Shuai Tang, Hailin Jin, Chen Fang et al.

Context plays an important role in human language understanding, thus it may also be useful for machines learning vector representations of language. In this paper, we explore an asymmetric encoder-decoder structure for unsupervised context-based sentence representation learning. We carefully designed experiments to show that neither an autoregressive decoder nor an RNN decoder is required. After that, we designed a model which still keeps an RNN as the encoder, while using a non-autoregressive convolutional decoder. We further combine a suite of effective designs to significantly improve model efficiency while also achieving better performance. Our model is trained on two different large unlabelled corpora, and in both cases the transferability is evaluated on a set of downstream NLP tasks. We empirically show that our model is simple and fast while producing rich sentence representations that excel in downstream tasks.

Shuai Tang, Hailin Jin, Chen Fang et al.

The skip-thought model has been proven to be effective at learning sentence representations and capturing sentence semantics. In this paper, we propose a suite of techniques to trim and improve it. First, we validate a hypothesis that, given a current sentence, inferring the previous and inferring the next sentence provide similar supervision power, therefore only one decoder for predicting the next sentence is preserved in our trimmed skip-thought model. Second, we present a connection layer between encoder and decoder to help the model to generalize better on semantic relatedness tasks. Third, we found that a good word embedding initialization is also essential for learning better sentence representations. We train our model unsupervised on a large corpus with contiguous sentences, and then evaluate the trained model on 7 supervised tasks, which includes semantic relatedness, paraphrase detection, and text classification benchmarks. We empirically show that, our proposed model is a faster, lighter-weight and equally powerful alternative to the original skip-thought model.

Shuai Tang, Hailin Jin, Chen Fang et al.

We study the skip-thought model with neighborhood information as weak supervision. More specifically, we propose a skip-thought neighbor model to consider the adjacent sentences as a neighborhood. We train our skip-thought neighbor model on a large corpus with continuous sentences, and then evaluate the trained model on 7 tasks, which include semantic relatedness, paraphrase detection, and classification benchmarks. Both quantitative comparison and qualitative investigation are conducted. We empirically show that, our skip-thought neighbor model performs as well as the skip-thought model on evaluation tasks. In addition, we found that, incorporating an autoencoder path in our model didn't aid our model to perform better, while it hurts the performance of the skip-thought model.