17 citations · 99 across the 66 of their papers we have counts for
80 papers
ForkGRPO: Efficient Exploration and Fine-Grained Credit Assignment for Diffusion Language Models
Zhaoyan Jia, Chengwei Zhou, Gourav Datta +1
Diffusion large language models (dLLMs) have advanced rapidly, yet strengthening their reasoning through reinforcement learning (RL) remains an open challenge. Any-order generation…
The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow
Arya Fayyazi, Mehdi Kamal, Massoud Pedram
Language-model agents sometimes act beyond their authorization and then misreport what they did. On CAPE-Bench, matched agent tasks in which one fact decides whether an action is a…
The Sharp Directions Are Against You: Curvature Analysis of Activation Steering
Seyedarmin Azizi, Arya Fayyazi, Parsa Razmara +3
Activation steering adds a vector to a language model's internal representations at inference time. It is a lightweight alternative to fine-tuning for behavioral control. The stand…
Stateless Stochastic Computing for Generative AI on Superconducting Logic: A Model-Hardware Co-Design
Mehdi Kamal, Massoud Pedram
Thermodynamic computing lets stochastic physical dynamics carry out a computation and reads out the result as a time average. Recently, thermodynamic computing has been demonstrate…
Running Fewer Loops Removes Refusal Behaviour in Recurrent-Depth Language Models
Seyedarmin Azizi, Erfan Baghaei Potraghloo, Arya Fayyazi +2
A recurrent-depth language model reuses one block of weights several times in a row. The number of repetitions, which we call loops, is chosen when the model runs, not when it is t…
Sharpen Without Search: On-Policy Distillation of Sequence-Level Power Distribution
Erfan Baghaei Potraghloo, Seyedarmin Azizi, Arya Fayyazi +4
A language model can give a correct answer more probability than any single incorrect answer and still usually sample an incorrect one, because the incorrect answers together hold…
Labels Override Definitions in Jev-Style Typed Decision Models
Seyedarmin Azizi, Erfan Baghaei Potraghloo, Massoud Pedram
A typed decision model answers a fixed question about an input by returning a probability for each of several caller-defined options. Each option carries a short label and a writte…
Chopthin-Consensus Power Sampling: A Diversity-Preserving Approach to LLM Decoding
Minoo Ahmadi, Seyedarmin Azizi, Erfan Baghaei Potraghloo +2
Inference-time power sampling via Sequential Monte Carlo (SMC) can substantially improve large language model (LLM) reasoning without requiring post-training. However, many existin…
RIVERPlace: Repairing Interconnect Violations with Efficient Retiming and Incremental Placement for AQFP Circuits
Robert S. Aviles, Ziyu Liu, Sasan Razmkhah +2
The Adiabatic Quantum-Flux-Parametron (AQFP) offers near-Landauer-limit energy efficiency but faces significant scalability challenges due to strict path balancing and limited driv…
Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders
Chan Aristella Lu, Arya Fayyazi, Junhao Zhang +6
Fairness audits for LLM-based recommenders have largely focused on observable outputs, implicitly assuming that stable recommendations reflect stable internal processing. We challe…
Multi-Level Modeling of Large Language Model Inference Latency and Energy via Hybrid Analytical--Machine-Learning Predictors
Saeid Shokoufa, Mohammad Erfan Sadeghi, Mehdi Kamal +1
The rapid scaling of Large Language Models (LLMs) has significantly increased computational cost, energy consumption, and inference latency, making accurate estimation essential fo…
COFT: Counterfactual-Conformal Decoding for Fair Chain-of-Thought Reasoning in Large Language Models
Arya Fayyazi, Mehdi Kamal, Massoud Pedram
Large language models (LLMs) can reveal and amplify societal biases during chain-of-thought (CoT) generation. We present COFT (Chain of Fair Thought), a training-free decoding meth…
One Token Away from Collapse: The Fragility of Instruction-Tuned Helpfulness
Erfan Baghaei Potraghloo, Seyedarmin Azizi, Souvik Kundu +1
Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints…
TimingLLM: A Two-Stage Retrieval-Augmented Framework for Pre-Synthesis Timing Prediction from Verilog
Armin Abdollahi, Negin Ashrafi, Mehdi Kamal +1
Early, tool-free prediction of post-synthesis timing remains a key obstacle to rapid RTL iteration. We introduce TimingLLM, a two-stage retrieval-augmented LLM pipeline that estima…
Sense Less, Infer More: Agentic Multimodal Transformers for Edge Medical Intelligence
Chengwei Zhou, Zhaoyan Jia, Haotian Yu +6
Edge-based multimodal medical monitoring requires models that balance diagnostic accuracy with severe energy constraints. Continuous acquisition of ECG, PPG, EMG, and IMU streams r…
qPRO-AQFP: Post-Routing Optimization of AQFP Circuits with Delay Line Clocking
Robert S. Aviles, Ziyu Liu, Jingkai Hong +3
Adiabatic Quantum-Flux-Parametron (AQFP) logic is an ultra-low-power superconducting logic family with energy consumption approaching the Shannon limit, making it attractive for qu…
Power-SMC: Low-Latency Sequence-Level Power Sampling for Training-Free LLM Reasoning
Seyedarmin Azizi, Erfan Baghaei Potraghloo, Minoo Ahmadi +2
Reasoning ability in large language models is often attributed to \emph{distribution sharpening}: concentrating output probability on high-likelihood sequences. Recent works show t…
HDLFORGE: A Two-Stage Multi-Agent Framework for Efficient Verilog Code Generation with Adaptive Model Escalation
Armin Abdollahi, Saeid Shokoufa, Negin Ashrafi +2
We present HDLFORGE, a two-stage multi-agent framework for automated Verilog generation that optimizes the trade-off between generation speed and accuracy. The system uses a compac…
Inductorless Fast Phase Logic: Enabling Two-Order-of-Magnitude Density Scaling for Superconductor VLSI
Sasan Razmkhah, Douglas Scott Holmes, Massoud Pedram
Fast phase logic (FPL) is a novel digital superconductor electronic (SCE) logic family that employs multiple junction types, including switching 0-Josephson junctions (0-JJs), non-…
SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models
Jiayi Tian, Seyedarmin Azizi, Yequan Zhao +7
Large reasoning models (LRMs) often incur significant key-value (KV) cache overhead, due to their linear growth with the verbose chain-of-thought (CoT) reasoning. This incurs both…
SuperSNN: A Hardware-Aware Framework for Physically Realizable, High-Performance Superconducting Spiking Neural Network Chips
Changxu Song, Arda Caliskan, Beyza Zeynep Ucpinar +5
Despite numerous proposed designs for superconducting neural networks (SNNs), most have overlooked practical fabrication constraints, leading to implementations limited to only a f…
Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation
Erfan Baghaei Potraghloo, Seyedarmin Azizi, Souvik Kundu +1
Large language models (LLMs), despite their impressive performance across a wide range of tasks, often struggle to balance two competing objectives in open-ended text generation: f…
SCE-NTT: A Hardware Accelerator for Number Theoretic Transform Using Superconductor Electronics
Sasan Razmkhah, Mingye Li, Zeming Cheng +13
This research explores the use of superconductor electronics (SCE) for accelerating fully homomorphic encryption (FHE), focusing on the Number-Theoretic Transform (NTT), a key comp…
Activation Steering for Chain-of-Thought Compression
Seyedarmin Azizi, Erfan Baghaei Potraghloo, Massoud Pedram
Large language models (LLMs) excel at complex reasoning when they include intermediate steps, known as "chains of thought" (CoTs). However, these rationales are often overly verbos…