Related papers: TorR: Towards Brain-Inspired Task-Oriented Reasoni…
In text-audio retrieval (TAR) tasks, due to the heterogeneity of contents between text and audio, the semantic information contained in the text is only similar to certain frames within the audio. Yet, existing works aggregate the entire…
Chain-of-Thought (CoT) is a critical technique in enhancing the reasoning ability of Large Language Models (LLMs), and latent reasoning methods have been proposed to accelerate the inefficient token-level reasoning chain. We notice that…
Energy-harvesting-powered computing offers intriguing and vast opportunities to dramatically transform the landscape of the Internet of Things (IoT) devices by utilizing ambient sources of energy to achieve battery-free computing. In order…
Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token decoding mechanism inherent in traditional autoregressive…
Attention-based motion aggregation concepts have recently shown their usefulness in optical flow estimation, in particular when it comes to handling occluded regions. However, due to their complexity, such concepts have been mainly…
DETR-like models have significantly boosted the performance of detectors and even outperformed classical convolutional models. However, all tokens are treated equally without discrimination brings a redundant computational burden in the…
Feedforward geometric foundation models achieve strong short-window reconstruction, yet scaling them to minutes-long videos is bottlenecked by quadratic attention complexity or limited effective memory in recurrent designs. We present LoGeR…
The evolution toward 6G networks demands a fundamental shift from bit-centric transmission to semantic-aware communication that emphasizes task-relevant information. This work introduces TOAST (Task-Oriented Adaptive Semantic Transmission),…
Reasoning is a fundamental capability of Large Language Models. While prior research predominantly focuses on enhancing narrow skills like math or code generation, improving performance on many other reasoning tasks remains challenging due…
Engineers learn from every design they create, building intuition that helps them quickly identify promising solutions for new problems. Topology optimization (TO) - a well-established computational method for designing structures with…
Most referring object detection (ROD) models, especially the modern grounding detectors, are designed for data-rich conditions, yet many practical deployments, such as robotics, augmented reality, and other specialized domains, would face…
Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs), yet it incurs substantial computational overhead for inference. Existing CoT compression methods often suffer from a critical…
Communication scheduling has been shown to be effective in accelerating distributed training, which enables all-reduce communications to be overlapped with backpropagation computations. This has been commonly adopted in popular distributed…
Modern transformer-based encoder-decoder architectures struggle with reasoning tasks due to their inability to effectively extract relational information between input objects (data/tokens). Recent work introduced the Abstractor module,…
Reasoning in Large Language Models (LLMs) often suffers from inefficient long chain-of-thought traces with redundant self-exploration and validation, which inflate computational costs and even degrade performance. Inspired by human…
Multi-step Chain-of-Thought (CoT) has significantly advanced the mathematical reasoning capabilities of LLMs by leveraging explicit reasoning steps. However, the widespread adoption of Long CoT often results in sequence lengths that exceed…
Recently, long-thought reasoning models achieve strong performance on complex reasoning tasks, but often incur substantial inference overhead, making efficiency a critical concern. Our empirical analysis reveals that the benefit of using…
Transformer inference requires high compute accuracy; achieving this using analog CIMs has been difficult due to inherent computational errors. To overcome this challenge, we propose a Capacitor-Reconfiguring CIM (CR-CIM) to realize high…
Composed Image Retrieval (CIR) is the task of retrieving a target image from a gallery using a composed query consisting of a reference image and a modification text. Among various CIR approaches, training-free zero-shot methods based on…
While deep learning succeeds in a wide range of tasks, it highly depends on the massive collection of annotated data which is expensive and time-consuming. To lower the cost of data annotation, active learning has been proposed to…