Copertina

Can We Trust LLMs on Memristors? Diving into Reasoning Ability under Non-Ideality

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Taiqiang, Cheng, Yuxin, Ding, Chenchen, Yang, Runming, Feng, Xincheng, Zhou, Wenyong, Liu, Zhengwu, Wong, Ngai
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

HaLoRA: Hardware-aware Low-Rank Adaptation for Large Language Models Based on Hybrid Compute-in-Memory Architecture
di: Wu, Taiqiang, et al.
Pubblicazione: (2025)

Perspective-aware 3D Gaussian Inpainting with Multi-view Consistency
di: Cheng, Yuxin, et al.
Pubblicazione: (2025)

Enhancing Robustness of Implicit Neural Representations Against Weight Perturbations
di: Zhou, Wenyong, et al.
Pubblicazione: (2025)

Distribution-Aware Hadamard Quantization for Hardware-Efficient Implicit Neural Representations
di: Zhou, Wenyong, et al.
Pubblicazione: (2025)

MINR: Efficient Implicit Neural Representations for Multi-Image Encoding
di: Zhou, Wenyong, et al.
Pubblicazione: (2025)

Re-Activating Frozen Primitives for 3D Gaussian Splatting
di: Cheng, Yuxin, et al.
Pubblicazione: (2025)

Revisiting Model Interpolation for Efficient Reasoning
di: Wu, Taiqiang, et al.
Pubblicazione: (2025)

QuadINR: Hardware-Efficient Implicit Neural Representations Through Quadratic Activation
di: Zhou, Wenyong, et al.
Pubblicazione: (2025)

ROMER: Expert Replacement and Router Calibration for Robust MoE LLMs on Analog Compute-in-Memory Systems
di: Zhou, Wenyong, et al.
Pubblicazione: (2026)

Binary Weight Multi-Bit Activation Quantization for Compute-in-Memory CNN Accelerators
di: Zhou, Wenyong, et al.
Pubblicazione: (2025)

The Art of Efficient Reasoning: Data, Reward, and Optimization
di: Wu, Taiqiang, et al.
Pubblicazione: (2026)

A Time- and Energy-Efficient CNN with Dense Connections on Memristor-Based Chips
di: Zhou, Wenyong, et al.
Pubblicazione: (2025)

Timber: Training-free Instruct Model Refining with Base via Effective Rank
di: Wu, Taiqiang, et al.
Pubblicazione: (2025)

Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models
di: Wu, Taiqiang, et al.
Pubblicazione: (2024)

Extending Straight-Through Estimation for Robust Neural Networks on Analog CIM Hardware
di: Feng, Yuannuo, et al.
Pubblicazione: (2025)

HPD: Hybrid Projection Decomposition for Robust State Space Models on Analog CIM Hardware
di: Feng, Yuannuo, et al.
Pubblicazione: (2025)

Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models
di: Xiao, He, et al.
Pubblicazione: (2025)

LoCa: Logit Calibration for Knowledge Distillation
di: Yang, Runming, et al.
Pubblicazione: (2024)

LLM-NEO: Parameter Efficient Knowledge Distillation for Large Language Models
di: Yang, Runming, et al.
Pubblicazione: (2024)

Shadow-FT: Tuning Instruct Model via Training on Paired Base Model
di: Wu, Taiqiang, et al.
Pubblicazione: (2025)

Decomposing Densification in Gaussian Splatting for Faster 3D Scene Reconstruction
di: Huang, Binxiao, et al.
Pubblicazione: (2025)

Mixture-of-Subspaces in Low-Rank Adaptation
di: Wu, Taiqiang, et al.
Pubblicazione: (2024)

Dual-Layer Architecture for Adaptive Cognitive Systems under Non-Ideality
di: Grossi Fernandez, David
Pubblicazione: (2026)

PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models
di: Xiao, He, et al.
Pubblicazione: (2025)

Quantization Meets Reasoning: Exploring and Mitigating Degradation of Low-Bit LLMs in Mathematical Reasoning
di: Li, Zhen, et al.
Pubblicazione: (2025)

Multicarrier ISAC: Advances in Waveform Design, Signal Processing and Learning under Non-Idealities
di: Koivunen, Visa, et al.
Pubblicazione: (2024)

Can We Trust LLM Detectors?
di: Sandhan, Jivnesh, et al.
Pubblicazione: (2026)

Stochastic Multivariate Universal-Radix Finite-State Machine: a Theoretically and Practically Elegant Nonlinear Function Approximator
di: Feng, Xincheng, et al.
Pubblicazione: (2024)

Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning
di: Li, Zhen, et al.
Pubblicazione: (2025)

Beyond-Diagonal RIS Under Non-Idealities: Learning-Based Architecture Discovery and Optimization
di: Zhou, Binggui, et al.
Pubblicazione: (2025)

Virtuality as the Ideality of the Information Society
di: Oksana B. KRUT
Pubblicazione: (2018)

Weight-Inherited Distillation for Task-Agnostic BERT Compression
di: Wu, Taiqiang, et al.
Pubblicazione: (2023)

The Memorization Problem: Can We Trust LLMs' Economic Forecasts?
di: Lopez-Lira, Alejandro, et al.
Pubblicazione: (2025)

ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection
di: Liu, Tao, et al.
Pubblicazione: (2026)

Model Evolution Under Zeroth-Order Optimization: A Neural Tangent Kernel Perspective
di: Zhang, Chen, et al.
Pubblicazione: (2026)

Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?
di: Hu, Yijie, et al.
Pubblicazione: (2025)

Can We Trust LLMs? Mitigate Overconfidence Bias in LLMs through Knowledge Transfer
di: Yang, Haoyan, et al.
Pubblicazione: (2024)

Nonparametric Teaching for Graph Property Learners
di: Zhang, Chen, et al.
Pubblicazione: (2025)

Edge-free but Structure-aware: Prototype-Guided Knowledge Distillation from GNNs to MLPs
di: Wu, Taiqiang, et al.
Pubblicazione: (2023)

InjectRBP: Steering Large Language Model Reasoning Behavior via Pattern Injection
di: Wu, Xiuping, et al.
Pubblicazione: (2026)