Parth H. Pathak

Tanveer Hannan, Dimitrios Mallios, Parth Pathak et al.

Large Vision-Language Models (LVLMs) have demonstrated strong multimodal reasoning capabilities on long and complex documents. However, their high memory footprint makes them impractical for deployment on resource-constrained edge devices. We present DocSLM, an efficient Small Vision-Language Model designed for long-document understanding under constrained memory resources. DocSLM incorporates a Hierarchical Multimodal Compressor that jointly encodes visual, textual, and layout information from each page into a fixed-length sequence, greatly reducing memory consumption while preserving both local and global semantics. To enable scalable processing over arbitrarily long inputs, we introduce a Streaming Abstention mechanism that operates on document segments sequentially and filters low-confidence responses using an entropy-based uncertainty calibrator. Across multiple long multimodal document benchmarks, DocSLM matches or surpasses state-of-the-art methods while using 82\% fewer visual tokens, 75\% fewer parameters, and 71\% lower latency, delivering reliable multimodal document understanding on lightweight edge devices. Code is available in the supplementary material.

Karen Hambardzumyan, Nicolas Baldwin, Edan Toledo et al.

Existing research has identified three structural performance bottlenecks in AI research agents: (1) synchronous single-GPU execution constrains sample throughput, limiting the benefit of search; (2) a generalization gap where validation-based selection causes performance to degrade over extended search horizons; and (3) the limited capability of fixed, single-turn LLM operators imposes a ceiling on search performance. We introduce AIRA$_2$, which addresses these bottlenecks through three architectural choices: an asynchronous multi-GPU worker pool that increases experiment throughput linearly; a Hidden Consistent Evaluation protocol that delivers a reliable evaluation signal; and ReAct agents that dynamically scope their actions and debug interactively. On MLE-bench-30, AIRA$_2$ achieves a mean Percentile Rank of 71.8% at 24 hours - surpassing the previous best of 69.9% - and steadily improves to 76.0% at 72 hours. Ablation studies reveal that each component is necessary and that the "overfitting" reported in prior work was driven by evaluation noise rather than true data memorization.

Tianyi Xu, Ding Zhang, Parth H. Pathak et al.

We consider a set of APs with unknown data rates that cooperatively serve a mobile client. The data rate of each link is i.i.d. sampled from a distribution that is unknown a priori. In contrast to traditional link scheduling problems under uncertainty, we assume that in each time step, the device can probe a subset of links before deciding which one to use. We model this problem as a contextual bandit problem with probing (CBwP) and present an efficient algorithm. We further establish the regret of our algorithm for links with Bernoulli data rates. Our CBwP model is a novel extension of the classic contextual bandit model and can potentially be applied to a large class of sequential decision-making problems that involve joint probing and play under uncertainty.

Dom Huh, Sai Gurrapu, Frederick Olson et al.

With advancements in deep model architectures, tasks in computer vision can reach optimal convergence provided proper data preprocessing and model parameter initialization. However, training on datasets with low feature-richness for complex applications limit and detriment optimal convergence below human performance. In past works, researchers have provided external sources of complementary data at the cost of supplementary hardware, which are fed in streams to counteract this limitation and boost performance. We propose a generative multi-stream architecture, eliminating the need for additional hardware with the intent to improve feature richness without risking impracticability. We also introduce the compact spatio-temporal residual block to the standard 3-dimensional convolutional model, C3D. Our rC3D model performs comparatively to the top C3D residual variant architecture, the pseudo-3D model, on the FASL-RGB dataset. Our methods have achieved 95.62% validation accuracy with a variance of 1.42% from training, outperforming past models by 0.45% in validation accuracy and 5.53% in variance.

Al Amin Hosain, Panneer Selvam Santhalingam, Parth Pathak et al.

American Sign Language recognition is a difficult gesture recognition problem, characterized by fast, highly articulate gestures. These are comprised of arm movements with different hand shapes, facial expression and head movements. Among these components, hand shape is the vital, often the most discriminative part of a gesture. In this work, we present an approach for effective learning of hand shape embeddings, which are discriminative for ASL gestures. For hand shape recognition our method uses a mix of manually labelled hand shapes and high confidence predictions to train deep convolutional neural network (CNN). The sequential gesture component is captured by recursive neural network (RNN) trained on the embeddings learned in the first stage. We will demonstrate that higher quality hand shape models can significantly improve the accuracy of final video gesture classification in challenging conditions with variety of speakers, different illumination and significant motion blurr. We compare our model to alternative approaches exploiting different modalities and representations of the data and show improved video gesture recognition accuracy on GMU-ASL51 benchmark dataset

Al Amin Hosain, Panneer Selvam Santhalingam, Parth Pathak et al.

Voice-controlled personal and home assistants (such as the Amazon Echo and Apple Siri) are becoming increasingly popular for a variety of applications. However, the benefits of these technologies are not readily accessible to Deaf or Hard-ofHearing (DHH) users. The objective of this study is to develop and evaluate a sign recognition system using multiple modalities that can be used by DHH signers to interact with voice-controlled devices. With the advancement of depth sensors, skeletal data is used for applications like video analysis and activity recognition. Despite having similarity with the well-studied human activity recognition, the use of 3D skeleton data in sign language recognition is rare. This is because unlike activity recognition, sign language is mostly dependent on hand shape pattern. In this work, we investigate the feasibility of using skeletal and RGB video data for sign language recognition using a combination of different deep learning architectures. We validate our results on a large-scale American Sign Language (ASL) dataset of 12 users and 13107 samples across 51 signs. It is named as GMUASL51. We collected the dataset over 6 months and it will be publicly released in the hope of spurring further machine learning research towards providing improved accessibility for digital assistants.

Hao Fu, Zizhan Zheng, Aveek K. Das et al.

The exponential growth of mobile devices has raised concerns about sensitive data leakage. In this paper, we make the first attempt to identify suspicious location-related HTTP transmission flows from the user's perspective, by answering the question: Is the transmission user-intended? In contrast to previous network-level detection schemes that mainly rely on a given set of suspicious hostnames, our approach can better adapt to the fast growth of app market and the constantly evolving leakage patterns. On the other hand, compared to existing system-level detection schemes built upon program taint analysis, where all sensitive transmissions as treated as illegal, our approach better meets the user needs and is easier to deploy. In particular, our proof-of-concept implementation (FlowIntent) captures sensitive transmissions missed by TaintDroid, the state-of-the-art dynamic taint analysis system on Android platforms. Evaluation using 1002 location sharing instances collected from more than 20,000 apps shows that our approach achieves about 91% accuracy in detecting illegitimate location transmissions.