Aadi Palnitkar

Xiaomin Lin, Vivek Mange, Arjun Suresh et al.

Oysters are a vital keystone species in coastal ecosystems, providing significant economic, environmental, and cultural benefits. As the importance of oysters grows, so does the relevance of autonomous systems for their detection and monitoring. However, current monitoring strategies often rely on destructive methods. While manual identification of oysters from video footage is non-destructive, it is time-consuming, requires expert input, and is further complicated by the challenges of the underwater environment. To address these challenges, we propose a novel pipeline using stable diffusion to augment a collected real dataset with realistic synthetic data. This method enhances the dataset used to train a YOLOv10-based vision model. The model is then deployed and tested on an edge platform in underwater robotics, achieving a state-of-the-art 0.657 mAP@50 for oyster detection on the Aqua2 platform.

Hitesh Kyatham, Arjun Suresh, Aadi Palnitkar et al.

The underwater domain presents a vast array of challenges for roboticists and computer vision researchers alike, such as poor lighting conditions and high dynamic range scenes. In these adverse conditions, traditional vision techniques struggle to adapt and lead to suboptimal performance. Event-based cameras present an attractive solution to this problem, mitigating the issues of traditional cameras by tracking changes in the footage on a frame-by-frame basis. In this paper, we introduce a pipeline which can be used to generate realistic synthetic data of an event-based camera mounted to an AUV (Autonomous Underwater Vehicle) in an underwater environment for training vision models. We demonstrate the effectiveness of our pipeline using the task of rock detection with poor visibility and suspended particulate matter, but the approach can be generalized to other underwater tasks.

Aadi Palnitkar, Mingyang Mao, Nicholas Waytowich et al.

As large language models (LLMs) are applied to increasingly longer and more complex tasks, there is a growing need for realistic long-context benchmarks that require selective reading and integration of heterogeneous, multi-modal information sources. This need is especially acute for geospatial planning problems, such as those found in planning for large-scale military operations, which demand fast and accurate reasoning over maps, orders, intelligence reports, and other distributed data. To address this gap, we present MilSCORE (Military Scenario Contextual Reasoning), to our knowledge the first scenario-level dataset of expert-authored, multi-hop questions grounded in a complex, simulated military planning scenario used for training. MilSCORE is designed to evaluate high-stakes decision-making and planning, probing LLMs' ability to combine tactical and spatial reasoning across multiple sources and to reason over long-horizon, geospatially rich context. The benchmark includes a diverse set of question types across seven categories targeting both factual recall and multi-step reasoning about constraints, strategy, and spatial analysis. We provide an evaluation protocol and report baseline results for a range of contemporary vision-language models. Our findings highlight substantial headroom on MilSCORE, indicating that current systems struggle with realistic, scenario-level long-context planning, and positioning MilSCORE as a challenging testbed for future work.

Minghui Liu, Aadi Palnitkar, Tahseen Rabbani et al.

Large language models (LLMs) have demonstrated remarkable performance on long-context tasks, but are often bottlenecked by memory constraints. Namely, the KV cache, which is used to significantly speed up attention computations, grows linearly with context length. A suite of compression algorithms has been introduced to alleviate cache growth by evicting unimportant tokens. However, several popular strategies are targeted towards the prefill phase, i.e., processing long prompt context, and their performance is rarely assessed on reasoning tasks requiring long decoding. In particular, short but complex prompts, such as those in benchmarks like GSM8K and MATH500, often benefit from multi-step reasoning and self-reflection, resulting in thinking sequences thousands of tokens long. In this work, we benchmark the performance of several popular compression strategies on long-reasoning tasks. For the non-reasoning Llama-3.1-8B-Instruct, we determine that no singular strategy fits all, and that performance is heavily influenced by dataset type. However, we discover that H2O and our decoding-enabled variant of SnapKV are dominant strategies for reasoning models, indicating the utility of heavy-hitter tracking for reasoning traces. We also find that eviction strategies at low budgets can produce longer reasoning traces, revealing a tradeoff between cache size and inference costs.

Aadi Palnitkar, Arjun Suresh, Rishi Rajesh et al.

Increasingly, more and more people are turning to large language models (LLMs) for healthcare advice and consultation, making it important to gauge the efficacy and accuracy of the responses of LLMs to such queries. While there are pre-existing medical benchmarks literature which seeks to accomplish this very task, these benchmarks are almost universally in English, which has led to a notable gap in existing literature pertaining to multilingual LLM evaluation. Within this work, we seek to aid in addressing this gap with Cancer-Myth-Indic, an Indic language benchmark built by translating a 500-item subset of Cancer-Myth, sampled evenly across its original categories, into five under-served but widely used languages from the subcontinent (500 per language; 2,500 translated items total). Native-speaker translators followed a style guide for preserving implicit presuppositions in translation; items feature false presuppositions relating to cancer. We evaluate several popular LLMs under this presupposition stress.

Tasnim Kabir, Dmytro Kurdydyk, Aadi Palnitkar et al.

Existing audio question answering benchmarks largely emphasize sound event classification or caption-grounded queries, often enabling models to succeed through shortcut strategies, short-duration cues, lexical priors, dataset-specific biases, or even bypassing audio via metadata and captions rather than genuine reasoning Thus, we present AUDITA (Audio Understanding from Diverse Internet Trivia Authors), a large-scale, real-world benchmark to rigorously evaluate audio reasoning beyond surface-level acoustic recognition. AUDITA comprises carefully curated, human-authored trivia questions grounded in real-world audio, designed to stress robust auditory reasoning through challenging distractors and long-range temporal dependencies, using probing queries that cannot be answered from isolated text or sound cues alone. Human average accuracy of 32.13% shows both the challenge of the task while demonstrating meaningful comprehension of the audio. In stark contrast, state of-the-art audio question answering models perform poorly, with average accuracy below 8.86%. Beyond raw accuracy, we apply Item Response Theory (IRT) to estimate latent proficiency, question difficulty, and expose systematic deficiencies of the models and data.