Search Results for author:
Found 26 papers, 11 papers with code
Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching
To enhance communication efficiency, M2Cache maintains a neuron-level mixed-precision LRU cache in HBM, a larger layer-aware cache in DRAM, and a full model in SSD.
Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts
The core idea of Flex-MoE is to first address missing modalities using a new missing modality bank that integrates observed modality combinations with the corresponding missing ones.
Glider: Global and Local Instruction-Driven Expert Router
Our experiments using T5-based models for T0 and FLAN tasks demonstrate that GLIDER achieves substantially improved held-in performance while maintaining strong generalization on held-out tasks.
Accelerating the discovery of low-energy structure configurations: a computational approach that integrates first-principles calculations, Monte Carlo sampling, and Machine Learning
Finding Minimum Energy Configurations (MECs) is essential in fields such as physics, chemistry, and materials science, as they represent the most stable states of the systems.
AnyDesign: Versatile Area Fashion Editing via Mask-Free Diffusion
Moreover, these methods are limited in the variety of clothing types they can handle, as most datasets focus on people in clean backgrounds and only include generic garments such as tops, pants, and dresses.
Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep Graph Neural Networks
In this paper, we systematically analyze the real dominant problem in deep GNNs and identify the issues that these GNNs towards addressing Over-smoothing essentially work on via empirical experiments and theoretical gradient analysis.
Mew: Multiplexed Immunofluorescence Image Analysis through an Efficient Multiplex Network
Recent advancements in graph-based approaches for multiplexed immunofluorescence (mIF) images have significantly propelled the field forward, offering deeper insights into patient-level phenotyping.
LDP: A Local Diffusion Planner for Efficient Robot Navigation and Collision Avoidance
The complex conditional distribution in local navigation needs training data to include diverse policy in diverse real-world scenarios; (2) Myopic Observation.
Human-like object concept representations emerge naturally in multimodal large language models
The conceptualization and categorization of natural objects in the human mind have long intrigued cognitive scientists and neuroscientists, offering crucial insights into human perception and cognition.
Multi-label Class Incremental Emotion Decoding with Augmented Emotional Semantics Learning
Specifically, we design an augmented emotional relation graph module with label disambiguation to handle the past-missing partial label problem.
Multi-level Shared Knowledge Guided Learning for Knowledge Graph Completion
In the task of Knowledge Graph Completion (KGC), the existing datasets and their inherent subtasks carry a wealth of shared knowledge that can be utilized to enhance the representation of knowledge triplets and overall performance.
Mean Aggregator Is More Robust Than Robust Aggregators Under Label Poisoning Attacks
Robustness to malicious attacks is of paramount importance for distributed learning.
Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approach
Large Language Models (LLMs) have catalyzed transformative advances across a spectrum of natural language processing tasks through few-shot or zero-shot prompting, bypassing the need for parameter tuning.
PathRL: An End-to-End Path Generation Method for Collision Avoidance via Deep Reinforcement Learning
However, two roadblocks arise for training a DRL policy that outputs paths: (1) The action space for potential paths often involves higher dimensions comparing to low-level commands, which increases the difficulties of training; (2) It takes multiple time steps to track a path instead of a single time step, which requires the path to predicate the interactions of the robot w. r. t.
Byzantine-Robust Decentralized Stochastic Optimization with Stochastic Gradient Noise-Independent Learning Error
Motivated by this observation, we introduce two variance reduction methods, stochastic average gradient algorithm (SAGA) and loopless stochastic variance-reduced gradient (LSVRG), to Byzantine-robust decentralized stochastic optimization for eliminating the negative effect of the stochastic gradient noise.
$P^{3}O$: Transferring Visual Representations for Reinforcement Learning via Prompting
In particular, we specify a prompt-transformer for representation conversion and propose a two-step training process to train the prompt-transformer for the target environment, while the rest of the DRL pipeline remains unchanged.
Deep Reinforcement Learning for Localizability-Enhanced Navigation in Dynamic Human Environments
The planner learns to assign different importance to the geometric features and encourages the robot to navigate through areas that are helpful for laser localization.
TLP: A Deep Learning-based Cost Model for Tensor Program Tuning
Instead of extracting features from the tensor program itself, TLP extracts features from the schedule primitives.
Enhancing Distributional Stability among Sub-populations
shifts in prediction mechanisms ($Y|X$-shifts).
Reinforcement Learning for Robot Navigation with Adaptive Forward Simulation Time (AFST) in a Semi-Markov Model
Deep reinforcement learning (DRL) algorithms have proven effective in robot navigation, especially in unknown environments, by directly mapping perception inputs into robot control commands.
One-photon Solutions to Multiqubit Multimode quantum Rabi model
General solutions to the quantum Rabi model involve subspaces with unbounded number of photons.
Quantum Physics Optics
Constructing new APN functions through relative trace functions
With the help of this characterization, we obtain an infinite family of APN functions for $ n=2m $ with $m$ being an odd positive integer: $ f(x)=a{\rm Tr}^{n}_{m}(bx^3)+a^q{\rm Tr}^{n}_{m}(b^3x^9) $, where $ a\in \mathbb{F}_{2^n}$ such that $ a+a^q\neq 0 $ and $ b $ is a non-cube in $ \mathbb{F}_{2^n} $.
Information Theory Information Theory
Byzantine-Robust Variance-Reduced Federated Learning over Distributed Non-i.i.d. Data
We prove that the proposed method reaches a neighborhood of the optimal solution at a linear convergence rate and the learning error is determined by the number of Byzantine workers.
Byzantine-Robust Decentralized Stochastic Optimization over Static and Time-Varying Networks
In this paper, we consider the Byzantine-robust stochastic optimization problem defined over decentralized static and time-varying networks, where the agents collaboratively minimize the summation of expectations of stochastic local cost functions, but some of the agents are unreliable due to data corruptions, equipment failures or cyber-attacks.
Estimating Time-Varying Graphical Models
In this paper, we study time-varying graphical models based on data measured over a temporal grid.
Learning directed acyclic graphs via bootstrap aggregating
Specifically, an ensemble of DAGs is first learned based on bootstrap resamples of the data and then an aggregated DAG is derived by minimizing the overall distance to the entire ensemble.
