Search Results for author:
Found 26 papers, 8 papers with code
Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging
Model merging, on the other hand, offers a cost-effective and robust alternative by integrating the quick-thinking capabilities of System 1 models with the methodical reasoning of System 2 models.
Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks
The widespread deployment of pre-trained language models (PLMs) has exposed them to textual backdoor attacks, particularly those planted during the pre-training stage.
CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference
Large language models (LLMs) achieve impressive performance by scaling model parameters, but this comes with significant inference overhead.
KVTuner: Sensitivity-Aware Layer-wise Mixed Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference
KV cache quantization can improve Large Language Models (LLMs) inference throughput and latency in long contexts and large batch-size scenarios while preserving LLMs effectiveness.
MixPE: Quantization and Hardware Co-design for Efficient LLM Inference
Transformer-based large language models (LLMs) have achieved remarkable success as model sizes continue to grow, yet their deployment remains challenging due to significant computational and memory demands.
FuseGPT: Learnable Layers Fusion of Generative Pre-trained Transformers
In this paper, we propose FuseGPT, a novel methodology to recycle the pruned transformer blocks to further recover the model performance.
The Graph's Apprentice: Teaching an LLM Low Level Knowledge for Circuit Quality Estimation
Logic synthesis is a crucial phase in the circuit design process, responsible for transforming hardware description language (HDL) designs into optimized netlists.
HardCore Generation: Generating Hard UNSAT Problems for Data Augmentation
In this paper we address both by identifying and manipulating the key contributors to a problem's ``hardness'', known as cores.
GraSS: Combining Graph Neural Networks with Expert Knowledge for SAT Solver Selection
In this paper we present GraSS, a novel approach for automatic SAT solver selection based on tripartite graph representations of instances and a heterogeneous graph neural network (GNN) model.
DiLA: Enhancing LLM Tool Learning with Differential Logic Layer
In this paper, we propose a novel differential logic layer-aided language modeling (DiLA) approach, where logical constraints are integrated into the forward and backward passes of a network layer, to provide another option for LLM tool learning.
BetterV: Controlled Verilog Generation with Discriminative Guidance
In this work, we propose a Verilog generation framework, BetterV, which fine-tunes the large language models (LLMs) on processed domain-specific datasets and incorporates generative discriminators for guidance on particular design demands.
Machine Learning Insides OptVerse AI Solver: Design Principles and Applications
To this end, we present a comprehensive study on the integration of machine learning (ML) techniques into Huawei Cloud's OptVerse AI Solver, which aims to mitigate the scarcity of real-world mathematical programming instances, and to surpass the capabilities of traditional optimization techniques.
LLM4EDA: Emerging Progress in Large Language Models for Electronic Design Automation
Since circuit can be represented with HDL in a textual format, it is reasonable to question whether LLMs can be leveraged in the EDA field to achieve fully automated chip design and generate circuits with improved power, performance, and area (PPA).
DeepGate2: Functionality-Aware Circuit Representation Learning
Circuit representation learning aims to obtain neural representations of circuit elements and has emerged as a promising research direction that can be applied to various EDA and logic reasoning tasks.
Conflict-driven Structural Learning Towards Higher Coverage Rate in ATPG
(2) Conflict-driven implication and justification have been applied to increase decision accuracy and solving efficiency.
HardSATGEN: Understanding the Difficulty of Hard SAT Formula Generation and A Strong Structure-Hardness-Aware Baseline
On top of the observations that industrial formulae exhibit clear community structure and oversplit substructures lead to the difficulty in semantic formation of logical structures, we propose HardSATGEN, which introduces a fine-grained control mechanism to the neural split-merge paradigm for SAT formula generation to better recover the structural and computational properties of the industrial benchmarks.
SATformer: Transformer-Based UNSAT Core Learning
This paper introduces SATformer, a novel Transformer-based approach for the Boolean Satisfiability (SAT) problem.
Branch Ranking for Efficient Mixed-Integer Programming via Offline Ranking-based Policy Learning
Deriving a good variable selection strategy in branch-and-bound is essential for the efficiency of modern mixed-integer programming (MIP) solvers.
A Survey for Solving Mixed Integer Programming via Machine Learning
This paper surveys the trend of leveraging machine learning to solve mixed integer programming (MIP) problems.
Machine Learning Methods in Solving the Boolean Satisfiability Problem
This paper reviews the recent literature on solving the Boolean satisfiability problem (SAT), an archetypal NP-complete problem, with the help of machine learning techniques.
Learning to Select Cuts for Efficient Mixed-Integer Programming
In the online A/B testing of the product planning problems with more than $10^7$ variables and constraints daily, Cut Ranking has achieved the average speedup ratio of 12. 42% over the production solver without any accuracy loss of solution.
Bilevel Learning Model Towards Industrial Scheduling
In this paper, we propose a Bilevel Deep reinforcement learning Scheduler, \textit{BDS}, in which the higher level is responsible for exploring an initial global sequence, whereas the lower level is aiming at exploitation for partial sequence refinements, and the two levels are connected by a sliding-window sampling mechanism.
Pareto Multi-Task Learning
Recently, a novel method is proposed to find one single Pareto optimal solution with good trade-off among different tasks by casting multi-task learning as multiobjective optimization.
A Batched Scalable Multi-Objective Bayesian Optimization Algorithm
The proposed algorithm uses the Bayesian neural network as the scalable surrogate model.
Nonlinear Collaborative Scheme for Deep Neural Networks
Different from them, in this paper, we aim to link the generalization ability of a deep network to optimizing a new objective function.
Unsupervised prototype learning in an associative-memory network
Unsupervised learning in a generalized Hopfield associative-memory network is investigated in this work.
