145 citations · 212 across the 13 of their papers we have counts for
15 papers
The polyharmonic Hénon--Lane--Emden conjecture
Phuong Le
We study positive classical solutions of the polyharmonic Hénon--Lane--Emden system , in , where , , , an…
MaskCoFT: Masked Co-Adaptive Fine-Tuning for Memory-Efficient MoE Inference
Junfeng Wu, Zehao Fan, Hadjer Benmeziane +3
Mixture-of-experts (MoE) language models often exceed the memory of a single GPU. Expert offloading keeps most experts in host memory and loads them on demand, so decoding speed de…
Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models
Ali Janati, Kaoutar El Maghraoui, Chengke Zou +4
Mixture-of-Experts (MoE) models decouple parameter count from per-token compute, but deployment still requires hosting every expert in memory. Recent theory shows that experts whos…
Synthetic Scenario Generation for Evaluation of Industry 4.0 Agents
Sagar Chethan Kumar, Rohith Kanathur, Dhaval Patel +1
Industrial agent benchmarks require realistic evaluation scenarios that integrate telemetry, failure modes, maintenance records, and domain standards. However, existing benchmarks…
Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents
Dhaval C. Patel, Kaoutar El Maghraoui, Shuxin Lin +58
Agent benchmarks are growing fast, but no single benchmark touches more than four or five of the dimensions that deployment exposes. This paper aggregates the largest coordinated d…
Internalizing Tool Knowledge in Small Language Models via QLoRA Fine-Tuning
Yuval Shemla, Ayal Yakobe, Tanmay Agarwal +2
Large language models are increasingly used as planning components in agentic systems, but current tool-use pipelines often require full tool schemas to be included in every prompt…
Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines
Alimurtaza Mustafa Merchant, Krish Veera, Sajal Kumar Goyla +3
Industrial asset operations workflows are latency-sensitive because a single user query may require coordination over sensor data, work orders, failure modes, forecasting tools, an…
PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools
Yusheng Li, Tianjun Feng, Yunfeng Chen +6
LLM agents are beginning to invoke industrial asset-management tools through the Model Context Protocol (MCP), yet whether they can act reliably on this substrate for safety-critic…
Sparse Attention Remapping with Clustering for Efficient LLM Decoding on PIM
Zehao Fan, Garrett Gagnon, Zhenyu Liu +1
Transformer-based models are the foundation of modern machine learning, but their execution, particularly during autoregressive decoding in large language models (LLMs), places sig…
A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts
Mohammed Nowaz Rabbani Chowdhury, Meng Wang, Kaoutar El Maghraoui +3
The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks, i.e., experts, through trainable routers. MoE reduces the training computa…
Analog In-Memory Computing with Uncertainty Quantification for Efficient Edge-based Medical Imaging Segmentation
Imane Hamzaoui, Hadjer Benmeziane, Zayneb Cherif +1
This work investigates the role of the emerging Analog In-memory computing (AIMC) paradigm in enabling Medical AI analysis and improving the certainty of these models at the edge.…
Grassroots Operator Search for Model Edge Adaptation
Hadjer Benmeziane, Kaoutar El Maghraoui, Hamza Ouarnoughi +1
Hardware-aware Neural Architecture Search (HW-NAS) is increasingly being used to design efficient deep learning architectures. An efficient and flexible search space is crucial to…
Using the IBM Analog In-Memory Hardware Acceleration Kit for Neural Network Training and Inference
Manuel Le Gallo, Corey Lammie, Julian Buechel +8
Analog In-Memory Computing (AIMC) is a promising approach to reduce the latency and energy consumption of Deep Neural Network (DNN) inference and training. However, the noisy and n…
AnalogNAS: A Neural Network Design Framework for Accurate Inference with Analog In-Memory Computing
Hadjer Benmeziane, Corey Lammie, Irem Boybat +9
The advancement of Deep Learning (DL) is driven by efficient Deep Neural Network (DNN) design and new hardware accelerators. Current DNN design is primarily tailored for general-pu…
A flexible and fast PyTorch toolkit for simulating training and inference on analog crossbar arrays
Malte J. Rasch, Diego Moreda, Tayfun Gokmen +6
We introduce the IBM Analog Hardware Acceleration Kit, a new and first of a kind open source toolkit to simulate analog crossbar arrays in a convenient fashion from within PyTorch…