Search Results for author:
Found 29 papers, 9 papers with code
Towards A Litmus Test for Common Sense
Aligning with the broader goal of developing beneficial AI without causing harm, our axiomatic litmus test not only diagnoses whether an AI can handle truly novel concepts but also provides a stepping stone toward an ethical, reliable foundation for future safe, beneficial, and aligned artificial intelligence.
VLTP: Vision-Language Guided Token Pruning for Task-Oriented Segmentation
We design a new pruning decoder to take both image tokens and vision-language guidance as input to predict the relevance of each image token to the task.
Boosting Online 3D Multi-Object Tracking through Camera-Radar Cross Check
In the domain of autonomous driving, the integration of multi-modal perception techniques based on data from diverse sensors has demonstrated substantial progress.
DεpS: Delayed ε-Shrinking for Faster Once-For-All Training
Hence, we propose Delayed $\epsilon$-Shrinking (D$\epsilon$pS) that starts the process of shrinking the full model when it is partially trained (~50%) which leads to training cost improvement and better in-place knowledge distillation to smaller models.
MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection
Monocular 3D object detection (Mono3D) holds noteworthy promise for autonomous driving applications owing to the cost-effectiveness and rich visual context of monocular camera sensors.
TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection
Nevertheless, the naive application of VLMs leads to sub-optimal quality, due to the misalignment between embeddings of object images and their visual attributes, which are mainly adjective phrases.
HDReason: Algorithm-Hardware Codesign for Hyperdimensional Knowledge Graph Reasoning
When conducting cross-models and cross-platforms comparison, HDReason yields an average 4. 2x higher performance and 3. 4x better energy efficiency with similar accuracy versus the state-of-the-art FPGA-based GCN training platform.
Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments
Motivated by recent research on extending the capabilities of LLMs with tools, we seek to investigate the intriguing potential of tools to augment LLMs in handling such complexity by introducing a novel class of tools, termed middleware, to aid in the proactive exploration within these massive environments.
VQPy: An Object-Oriented Approach to Modern Video Analytics
Video analytics is widely used in contemporary systems and services.
CenterRadarNet: Joint 3D Object Detection and Tracking Framework using 4D FMCW Radar
CenterRadarNet achieves the state-of-the-art result on the K-Radar 3D object detection benchmark.
Ethosight: A Reasoning-Guided Iterative Learning System for Nuanced Perception based on Joint-Embedding & Contextual Label Affinity
Traditional computer vision models often necessitate extensive data acquisition, annotation, and validation.
RecallM: An Adaptable Memory Mechanism with Temporal Understanding for Large Language Models
Unlike previous methods, the RecallM architecture is particularly effective at belief updating and maintaining a temporal understanding of the knowledge provided to it.
Ranked #1 on
Question Answering
on DuoRC
SuperFedNAS: Cost-Efficient Federated Neural Architecture Search for On-Device Inference
SuperFedNAS addresses these challenges by decoupling the training and search in federated NAS.
Adaptive Deep Neural Network Inference Optimization with EENet
Instead of having every sample go through all DNN layers during prediction, EENet learns an early exit scheduler, which can intelligently terminate the inference earlier for certain predictions, which the model has high confidence of early exit.
A Retrieve-and-Read Framework for Knowledge Graph Link Prediction
To address the limitations of existing KG link prediction frameworks, we propose a novel retrieve-and-read framework, which first retrieves a relevant subgraph context for the query and then jointly reasons over the context and the query with a high-capacity reader.
Ranked #2 on
Link Prediction
on FB15k-237
Learning Omnidirectional Flow in 360-degree Video via Siamese Representation
Optical flow estimation in omnidirectional videos faces two significant issues: the lack of benchmark datasets and the challenge of adapting perspective video-based methods to accommodate the omnidirectional nature.
Neurosymbolic Systems of Perception & Cognition: The Role of Attention
A cognitive architecture aimed at cumulative learning must provide the necessary information and control structures to allow agents to learn incrementally and autonomously from their experience.
Cross-View Exocentric to Egocentric Video Synthesis
Particularly, we propose a novel Bi-directional Spatial Temporal Attention Fusion Generative Adversarial Network (STA-GAN) to learn both spatial and temporal information to generate egocentric video sequences from the exocentric view.
A Metamodel and Framework for Artificial General Intelligence From Theory to Practice
This paper introduces a new metamodel-based knowledge representation that significantly improves autonomous learning and adaptation.
Learning Audio-Visual Correlations from Variational Cross-Modal Generation
People can easily imagine the potential sound while seeing an event.
Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset
To bridge this gap, in this paper we propose a novel Egocentric (first-person) 360{\deg} Kinetic human activity video dataset (EgoK360).
A Metamodel and Framework for AGI
Can artificial intelligence systems exhibit superhuman performance, but in critical ways, lack the intelligence of even a single-celled organism?
Exocentric to Egocentric Image Generation via Parallel Generative Adversarial Network
In this paper, we investigate exocentric (third-person) view to egocentric (first-person) view image generation.
Cascade Attention Guided Residue Learning GAN for Cross-Modal Translation
However, in machine learning, this cross-modal learning is a nontrivial task because different modalities have no homogeneous properties.
Improving Deep Models of Person Re-identification for Cross-Dataset Usage
Person re-identification (Re-ID) is the task of matching humans across cameras with non-overlapping views that has important applications in visual surveillance.
Metric Embedding Autoencoders for Unsupervised Cross-Dataset Transfer Learning
Cross-dataset transfer learning is an important problem in person re-identification (Re-ID).
Semantic Image Retrieval by Uniting Deep Neural Networks and Cognitive Architectures
Image and video retrieval by their semantic content has been an important and challenging task for years, because it ultimately requires bridging the symbolic/subsymbolic gap.
Knowledge-Defined Networking
In this paper, we explore the reasons for the lack of adoption and posit that the rise of two recent paradigms: Software-Defined Networking (SDN) and Network Analytics (NA), will facilitate the adoption of AI techniques in the context of network operation and control.
Networking and Internet Architecture
