About

Chandan Reddy is an Associate Professor in the Department of Gender, Women & Sexuality Studies at the University of Washington. He holds a B.A. in Literature from the University of California, an M.A. and Ph.D. in English/Comparative Literature from Columbia University. His fields of interest include Asian American studies, Critical Race Theory, Global Studies, Globalization Studies, Queer Studies, and Sexuality. Reddy's research encompasses topics such as queer kinships, Asian resident alien experiences, and subaltern politics, with recent works exploring militant motherhood in Kurdish resistance and queer migrations among P’urhépecha communities. He has taught courses on trans/gender queries, feminist social theory, and women’s studies, and has been actively involved in scholarly discussions and editorial roles, including serving as co-editor of GLQ. His contributions extend to advising research projects and engaging in public discussions on issues related to race, sexuality, and social justice.

Research topics

• Computer Science
• Artificial Intelligence
• Natural Language Processing
• Information Retrieval
• Programming language
• Linguistics

Selected publications

• SA-SSL-MOS: Self-Supervised Learning MOS Prediction with Spectral Augmentation for Generalized Multi-Rate Speech Assessment

  2026-04-21

  article
  PublisherDOI

• Distractor Injection Attacks on Large Reasoning Models: Characterization and Defense

  ArXiv.org · 2025-10-17

  preprintOpen accessSenior author

  Recent advances in large reasoning models (LRMs) have enabled remarkable performance on complex tasks such as mathematics and coding by generating long Chain-of-Thought (CoT) traces. In this paper, we identify and systematically analyze a critical vulnerability we term reasoning distraction, where LRMs are diverted from their primary objective by irrelevant yet complex tasks maliciously embedded in the prompt. Through a comprehensive study across diverse models and benchmarks, we show that even state-of-the-art LRMs are highly susceptible, with injected distractors reducing task accuracy by up to 60%. We further reveal that certain alignment techniques can amplify this weakness and that models may exhibit covert compliance, following hidden adversarial instructions in reasoning while concealing them in the final output. To mitigate these risks, we propose a training-based defense that combines Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) on synthetic adversarial data, improving robustness by over 50 points on challenging distractor attacks. Our findings establish reasoning distraction as a distinct and urgent threat to LRM reliability and provide a practical step toward safer and more trustworthy reasoning systems.

  PublisherOA PDFDOI

• SURFACEBENCH: A Geometry-Aware Benchmark for Symbolic Surface Discovery

  arXiv (Cornell University) · 2025-11-13

  preprintOpen accessSenior author

  Equation discovery from data is a central challenge in machine learning for science, which requires the recovery of concise symbolic expressions that govern complex physical and geometric phenomena. Recent large language model (LLM) approaches have shown promise in symbolic regression, yet existing benchmarks predominantly evaluate low-dimensional scalar functions and rely on string-level or regression-based metrics that fail to capture structural and geometric equivalence. We introduce SURFACEBENCH, the first geometry-aware benchmark for symbolic discovery of three-dimensional surfaces. Unlike scalar curve-fitting tasks, SURFACEBENCH targets surface-level reasoning, where multi-variable coupling, coordinate transformations, and geometric structure must be inferred directly from data. The benchmark comprises 183 analytically constructed, science-inspired surface equations across 15 categories and three representation paradigms: explicit, implicit, and parametric forms. Each task includes variable semantics and synthetically sampled 3D data, and is designed to stress symbolic composition, structural ambiguity, and representational non-uniqueness while mitigating memorization. To evaluate discovery quality, SURFACEBENCH incorporates symbolic equivalence checks with geometric metrics of the object-space (Chamfer and Hausdorff distances) and regression-based error measures, allowing evaluation of functional fidelity beyond algebraic syntax. Empirical evaluation across evolutionary, neural, and LLM-driven frameworks reveals that no current method achieves consistent performance across representation types, with LLM-based approaches exhibiting strong structural priors but limited robustness in parameter calibration and multi-equation reasoning.The code and data are available at this link: github.com/deep-symbolic-mathematics/surfacebench.

  PublisherOA PDFDOI

• MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training

  ArXiv.org · 2025-10-12

  preprintOpen accessSenior author

  Multi-turn Text-to-SQL aims to translate a user's conversational utterances into executable SQL while preserving dialogue coherence and grounding to the target schema. However, most existing systems only regard this task as a simple text translation task and follow a short-horizon paradigm, generating a query per turn without execution, explicit verification, and refinement, which leads to non-executable or incoherent outputs. We present MTSQL-R1, an agentic training framework for long-horizon multi-turn Text-to-SQL. We cast the task as a Markov Decision Process (MDP) in which an agent interacts with (i) a database for execution feedback and (ii) a persistent dialogue memory for coherence verification, performing an iterative propose to execute -> verify -> refine cycle until all checks pass. Experiments on COSQL and SPARC demonstrate that MTSQL-R1 consistently outperforms strong baselines, highlighting the importance of environment-driven verification and memory-guided refinement for conversational semantic parsing. Full recipes (including code, trained models, logs, reasoning trajectories, etc.) will be released after the internal review to contribute to community research.

  PublisherOA PDFDOI

• Towards Sub-millisecond Latency Real-Time Speech Enhancement Models on Hearables

  2025-03-12 · 3 citations

  article

  Low latency models are critical for real-time speech enhancement applications, such as hearing aids and hearables. However, the sub-millisecond latency space for resource-constrained hearables remains underexplored. We demonstrate speech enhancement using a computationally efficient minimum-phase FIR filter, enabling sample-by-sample processing to achieve mean algorithmic latency of 0.32 ms to 1.25 ms. With a single microphone, we observe a mean SI-SDRi of 4.1 dB. The approach shows generalization with a DNSMOS increase of 0.2 on unseen audio recordings. We use a lightweight LSTM-based model of 626k parameters to generate FIR taps. Using a real hardware implementation on a low-power DSP, our system can run with 376 MIPS and a mean end-to-end latency of 3.35 ms. In addition, we provide a comparison with existing low-latency spectral masking techniques. We hope this work will enable a better understanding of latency and can be used to improve the comfort and usability of hearables.

  PublisherDOI

• Selection of Layers from Self-supervised Learning Models for Predicting Mean-Opinion-Score of Speech

  2025-12-06

  article

  Self-supervised learning (SSL) models like Wav2Vec2, HuBERT, and WavLM have been widely used in speech processing. These transformer-based models consist of multiple layers, each capturing different levels of representation. While prior studies explored their layer-wise representations for efficiency and performance, speech quality assessment (SQA) models predominantly rely on last-layer features, leaving intermediate layers underexamined. In this work, we systematically evaluate different layers of multiple SSL models for predicting mean-opinion-score (MOS). Features from each layer are fed into a lightweight regression network to assess effectiveness. Our experiments consistently show early-layers features outperform or match those from the last layer, leading to significant improvements over conventional approaches and state-of-the-art MOS prediction models. These findings highlight the advantages of early-layer selection, offering enhanced performance and reduced system complexity.

  PublisherDOI

• Mitigating Selection Bias with Node Pruning and Auxiliary Options

  2025-01-01

  articleOpen accessSenior author
  PublisherOA PDFDOI

• KDD Workshop on Evaluation and Trustworthiness of Agentic and Generative AI

  2025-08-03

  articleOpen accessSenior author

  The rapid deployment of Generative and Agentic AI systems-ranging from large language models to autonomous agents-has created a critical need for rigorous and trustworthy evaluation methodologies. As these models influence real-world decision-making, traditional performance metrics alone fall short in capturing issues of safety, ethical alignment, misinformation, and human-centered usability. This workshop addresses these challenges by fostering interdisciplinary discussions and innovations in evaluation strategies that go beyond conventional benchmarks. Topics include holistic and multi-perspective assessments, scalable evaluation pipelines, reasoning and goal alignment in agentic behavior, misinformation detection, cross-modal generation, and trust calibration. By advancing robust, user-centric, and societally grounded evaluation practices, this workshop contributes to expanding KDD's methodological frontier into the emerging domain of responsible AI systems.

  PublisherOA PDFDOI

• DriveMind: A Dual Visual Language Model-based Reinforcement Learning Framework for Autonomous Driving

  arXiv (Cornell University) · 2025-06-01

  preprintOpen access

  End-to-end autonomous driving systems map sensor data directly to control commands, but remain opaque, lack interpretability, and offer no formal safety guarantees. While recent vision-language-guided reinforcement learning (RL) methods introduce semantic feedback, they often rely on static prompts and fixed objectives, limiting adaptability to dynamic driving scenes. We present DriveMind, a unified semantic reward framework that integrates: (i) a contrastive Vision-Language Model (VLM) encoder for stepwise semantic anchoring; (ii) a novelty-triggered VLM encoder-decoder, fine-tuned via chain-of-thought (CoT) distillation, for dynamic prompt generation upon semantic drift; (iii) a hierarchical safety module enforcing kinematic constraints (e.g., speed, lane centering, stability); and (iv) a compact predictive world model to reward alignment with anticipated ideal states. DriveMind achieves 19.4 +/- 2.3 km/h average speed, 0.98 +/- 0.03 route completion, and near-zero collisions in CARLA Town 2, outperforming baselines by over 4% in success rate. Its semantic reward generalizes zero-shot to real dash-cam data with minimal distributional shift, demonstrating robust cross-domain alignment and potential for real-world deployment.

  PublisherOA PDFDOI

• Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning

  ArXiv.org · 2025-04-08

  preprintOpen accessSenior author

  Recent advances in large-scale generative language models have shown that reasoning capabilities can significantly improve model performance across a variety of tasks. However, the impact of reasoning on a model's ability to mitigate stereotypical responses remains largely underexplored. In this work, we investigate the crucial relationship between a model's reasoning ability and fairness, and ask whether improved reasoning capabilities can mitigate harmful stereotypical responses, especially those arising due to shallow or flawed reasoning. We conduct a comprehensive evaluation of multiple open-source LLMs, and find that larger models with stronger reasoning abilities exhibit substantially lower stereotypical bias on existing fairness benchmarks. Building on this insight, we introduce ReGiFT -- Reasoning Guided Fine-Tuning, a novel approach that extracts structured reasoning traces from advanced reasoning models and infuses them into models that lack such capabilities. We use only general-purpose reasoning and do not require any fairness-specific supervision for bias mitigation. Notably, we see that models fine-tuned using ReGiFT not only improve fairness relative to their non-reasoning counterparts but also outperform advanced reasoning models on fairness benchmarks. We also analyze how variations in the correctness of the reasoning traces and their length influence model fairness and their overall performance. Our findings highlight that enhancing reasoning capabilities is an effective, fairness-agnostic strategy for mitigating stereotypical bias caused by reasoning flaws.

  PublisherOA PDFDOI

Recent grants

• III: Small: New Machine Learning Approaches for Modeling Time-to-Event Data

  NSF · $203k · 2016–2019

• Differential Network Interrogations of Epithelial to Mesenchymal Transition

  NIH · $160k · 2013–2015

• EAGER: Efficient Methods for Characterizing Large-Scale Network Dynamics

  NSF · $100k · 2012–2015

• EAGER: An Integrated Predictive Modeling Framework for Crowdfunding Environments

  NSF · $100k · 2016–2018

• III: Small: New Machine Learning Approaches for Modeling Time-to-Event Data

  NSF · $311k · 2015–2016

Frequent coauthors

• Ross Cutler

  Microsoft (United States)

  33 shared

• Issa Panahi

  The University of Texas at Dallas

  29 shared

• Andrea Tagarelli

  26 shared

• Ulrik Brandes

  ETH Zurich

  26 shared

• Moon Ho

  Columbia University

  25 shared

• Bill Fletcher

  New York University

  25 shared

• Martha Biondi

  Wayne State University

  25 shared

• Margaret Levi

  Stanford University

  25 shared

Labs

• Chandan Reddy LabPI

Education

• PhD, Computer Engineering

  Cornell University

  2007

Awards & honors

• 2023 Freedom Scholar by Marguerite Casey Foundation
• UW Simpson Center Awards (2022)