Search Results for author:
Found 20 papers, 6 papers with code
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks.
Interpreting and Steering LLMs with Mutual Information-based Explanations on Sparse Autoencoders
Large language models (LLMs) excel at handling human queries, but they can occasionally generate flawed or unexpected responses.
Robot Learning with Super-Linear Scaling
In this work, we propose Crowdsourcing and Amortizing Human Effort for Real-to-Sim-to-Real(CASHER), a pipeline for scaling up data collection and learning in simulation where the performance scales superlinearly with human effort.
InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma
InvestESG is a novel multi-agent reinforcement learning (MARL) benchmark designed to study the impact of Environmental, Social, and Governance (ESG) disclosure mandates on corporate climate investments.
Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion
To address this dilemma, we introduce TaylorMLP to protect the ownership of released LLMs and prevent their abuse.
DHP Benchmark: Are LLMs Good NLG Evaluators?
Large Language Models (LLMs) are increasingly serving as evaluators in Natural Language Generation (NLG) tasks.
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches
Long context capability is a crucial competency for large language models (LLMs) as it mitigates the human struggle to digest long-form texts.
Understanding Different Design Choices in Training Large Time Series Models
Moreover, we propose \emph{time series prompt}, a novel statistical prompting strategy tailored to time series data.
LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem
We find that with a simple, efficient, yet specific recipe, a backdoor LoRA can be trained once and then seamlessly merged (in a training-free fashion) with multiple task-enhancing LoRAs, retaining both its malicious backdoor and benign downstream capabilities.
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
However, there is a lack of in-depth studies that explore the element distribution of KV cache to understand the hardness and limitation of KV cache quantization.
Can Attention Be Used to Explain EHR-Based Mortality Prediction Tasks: A Case Study on Hemorrhagic Stroke
Stroke is a significant cause of mortality and morbidity, necessitating early predictive strategies to minimize risks.
NetBooster: Empowering Tiny Deep Learning By Standing on the Shoulders of Deep Giants
Tiny deep learning has attracted increasing attention driven by the substantial demand for deploying deep learning on numerous intelligent Internet-of-Things devices.
Gen-NeRF: Efficient and Generalizable Neural Radiance Fields via Algorithm-Hardware Co-Design
Novel view synthesis is an essential functionality for enabling immersive experiences in various Augmented- and Virtual-Reality (AR/VR) applications, for which generalizable Neural Radiance Fields (NeRFs) have gained increasing popularity thanks to their cross-scene generalization capability.
Robust Tickets Can Transfer Better: Drawing More Transferable Subnetworks in Transfer Learning
Transfer learning leverages feature representations of deep neural networks (DNNs) pretrained on source tasks with rich data to empower effective finetuning on downstream tasks.
Towards Fair Patient-Trial Matching via Patient-Criterion Level Fairness Constraint
To tackle these challenges, deep learning frameworks have been created to match patients to trials.
Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matching
The process of matching patients with suitable clinical trials is essential for advancing medical research and providing optimal care.
ERSAM: Neural Architecture Search For Energy-Efficient and Real-Time Social Ambiance Measurement
To this end, we propose a dedicated neural architecture search framework for Energy-efficient and Real-time SAM (ERSAM).
Recurrent Structure Attention Guidance for Depth Super-Resolution
Second, instead of the coarse concatenation guidance, we propose a recurrent structure attention block, which iteratively utilizes the latest depth estimation and the image features to jointly select clear patterns and boundaries, aiming at providing refined guidance for accurate depth recovery.
Structure Flow-Guided Network for Real Depth Super-Resolution
Specifically, our framework consists of a cross-modality flow-guided upsampling network (CFUNet) and a flow-enhanced pyramid edge attention network (PEANet).
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
Efficient deep neural network (DNN) models equipped with compact operators (e. g., depthwise convolutions) have shown great potential in reducing DNNs' theoretical complexity (e. g., the total number of weights/operations) while maintaining a decent model accuracy.
