Mayank Goel

Vimal Mollyn, Riku Arakawa, Mayank Goel et al.

Tracking body pose on-the-go could have powerful uses in fitness, mobile gaming, context-aware virtual assistants, and rehabilitation. However, users are unlikely to buy and wear special suits or sensor arrays to achieve this end. Instead, in this work, we explore the feasibility of estimating body pose using IMUs already in devices that many users own -- namely smartphones, smartwatches, and earbuds. This approach has several challenges, including noisy data from low-cost commodity IMUs, and the fact that the number of instrumentation points on a users body is both sparse and in flux. Our pipeline receives whatever subset of IMU data is available, potentially from just a single device, and produces a best-guess pose. To evaluate our model, we created the IMUPoser Dataset, collected from 10 participants wearing or holding off-the-shelf consumer devices and across a variety of activity contexts. We provide a comprehensive evaluation of our system, benchmarking it on both our own and existing IMU datasets.

Jacob-Junqi Tian, Hao Yu, Yury Orlovskiy et al.

This paper develops an agent-based automated fact-checking approach for detecting misinformation. We demonstrate that combining a powerful LLM agent, which does not have access to the internet for searches, with an online web search agent yields better results than when each tool is used independently. Our approach is robust across multiple models, outperforming alternatives and increasing the macro F1 of misinformation detection by as much as 20 percent compared to LLMs without search. We also conduct extensive analyses on the sources our system leverages and their biases, decisions in the construction of the system like the search tool and the knowledge base, the type of evidence needed and its impact on the results, and other parts of the overall process. By combining strong performance with in-depth understanding, we hope to provide building blocks for future search-enabled misinformation mitigation systems.

Jatin Kishnani, Mayank Goel, Amit Singh et al.

We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison of TPU and GPU platforms for large language model adaptation. Using LoRA on a Google TPU v5p-8 for training and TPU v6e-8 (Trillium) for inference, we document the full set of code-level adaptations required to port a GPU-native training recipe, built on PyTorch, HuggingFace TRL, and FSDP, to the JAX + Tunix/Qwix stack. These adaptations span mesh configuration, LoRA module naming conventions, sharding annotation corrections, gradient checkpointing, data pipeline restructuring, and a custom Orbax-to-safetensors checkpoint merging procedure. For inference, we detail the vLLM-TPU Docker setup necessary to serve Gemma 4 on v6e-8 and characterize the resulting latency and throughput profile. Compared with a 2xH100 GPU baseline under identical hyperparameters, TPU training completes 1.61x faster at 2.12x lower cost. Inference throughput is within 3% across platforms, while TPU achieves 2x lower time-to-first-token (235 ms vs. 475 ms). Together, the TPU configuration is 1.82x cheaper for a representative train-plus-service workload. Our work removes a critical gap in the open tooling ecosystem and provides practitioners with a reproducible, production-ready recipe for Gemma 4 deployment on TPU infrastructure.

Seungjoo Lee, Vimal Mollyn, Chris Harrison et al.

We present GlintMarkers, the first system to perform gaze-driven spatial perception using the inward-facing cameras on XR eyewear. Our key observation is that the cornea acts as a mirror that encodes both gaze direction and visual information about the environment in a small, low-contrast reflection. To extract spatial and semantic information from this reflection despite the camera's limited pixel budget, we present a passive retroreflective marker design that concentrates reflected near-infrared light onto the cornea, producing bright glint patterns. We develop a custom Perspective-n-Point (PnP) estimation framework adapted to corneal imaging and perform orientation and distance estimation of tagged objects, as well as unique object identification.

Mayank Goel, Venktesh V, Vikram Goyal

Math Word Problems (MWPs) in online assessments help test the ability of the learner to make critical inferences by interpreting the linguistic information in them. To test the mathematical reasoning capabilities of the learners, sometimes the problem is rephrased or the thematic setting of the original MWP is changed. Since manual identification of MWPs with similar problem models is cumbersome, we propose a tool in this work for MWP retrieval. We propose a hybrid approach to retrieve similar MWPs with the same problem model. In our work, the problem model refers to the sequence of operations to be performed to arrive at the solution. We demonstrate that our tool is useful for the mentioned tasks and better than semantic similarity-based approaches, which fail to capture the arithmetic and logical sequence of the MWPs. A demo of the tool can be found at https://www.youtube.com/watch?v=gSQWP3chFIs

Bijean Ghafouri, Shahrad Mohammadzadeh, James Zhou et al.

Large language models are increasingly relied upon as sources of information, but their propensity for generating false or misleading statements with high confidence poses risks for users and society. In this paper, we confront the critical problem of epistemic miscalibration $\unicode{x2013}$ where a model's linguistic assertiveness fails to reflect its true internal certainty. We introduce a new human-labeled dataset and a novel method for measuring the linguistic assertiveness of Large Language Models (LLMs) which cuts error rates by over 50% relative to previous benchmarks. Validated across multiple datasets, our method reveals a stark misalignment between how confidently models linguistically present information and their actual accuracy. Further human evaluations confirm the severity of this miscalibration. This evidence underscores the urgent risk of the overstated certainty LLMs hold which may mislead users on a massive scale. Our framework provides a crucial step forward in diagnosing this miscalibration, offering a path towards correcting it and more trustworthy AI across domains.

Haozhe Zhou, Riku Arakawa, Yuvraj Agarwal et al.

IMUs are regularly used to sense human motion, recognize activities, and estimate full-body pose. Users are typically required to place sensors in predefined locations that are often dictated by common wearable form factors and the machine learning model's training process. Consequently, despite the increasing number of everyday devices equipped with IMUs, the limited adaptability has seriously constrained the user experience to only using a few well-explored device placements (e.g., wrist and ears). In this paper, we rethink IMU-based motion sensing by acknowledging that signals can be captured from any point on the human body. We introduce IMU over Continuous Coordinates (IMUCoCo), a novel framework that maps signals from a variable number of IMUs placed on the body surface into a unified feature space based on their spatial coordinates. These features can be plugged into downstream models for pose estimation and activity recognition. Our evaluations demonstrate that IMUCoCo supports accurate pose estimation in a wide range of typical and atypical sensor placements. Overall, IMUCoCo supports significantly more flexible use of IMUs for motion sensing than the state-of-the-art, allowing users to place their sensors-laden devices according to their needs and preferences. The framework also supports the ability to change device locations depending on the context and suggests placement depending on the use case.

Tanishq Chaudhary, Mayank Goel, Radhika Mamidi

Well-defined jokes can be divided neatly into a setup and a punchline. While most works on humor today talk about a joke as a whole, the idea of generating punchlines to a setup has applications in conversational humor, where funny remarks usually occur with a non-funny context. Thus, this paper is based around two core concepts: Classification and the Generation of a punchline from a particular setup based on the Incongruity Theory. We first implement a feature-based machine learning model to classify humor. For humor generation, we use a neural model, and then merge the classical rule-based approaches with the neural approach to create a hybrid model. The idea behind being: combining insights gained from other tasks with the setup-punchline model and thus applying it to existing text generation approaches. We then use and compare our model with human written jokes with the help of human evaluators in a double-blind study.

Karan Ahuja, Abhishek Bose, Mohit Jain et al.

Autism often remains undiagnosed in adolescents and adults. Prior research has indicated that an autistic individual often shows atypical fixation and gaze patterns. In this short paper, we demonstrate that by monitoring a user's gaze as they watch commonplace (i.e., not specialized, structured or coded) video, we can identify individuals with autism spectrum disorder. We recruited 35 autistic and 25 non-autistic individuals, and captured their gaze using an off-the-shelf eye tracker connected to a laptop. Within 15 seconds, our approach was 92.5% accurate at identifying individuals with an autism diagnosis. We envision such automatic detection being applied during e.g., the consumption of web media, which could allow for passive screening and adaptation of user interfaces.