Papers

Introduction In the era of Large Language Models (LLMs), it is easy to assume that artificial intelligence has “solved” language. We can open ChatGPT, type a sentence in English, and instantly receive a fluent translation in French, Spanish, or Japanese. However, this apparent mastery masks a significant digital divide. While models like GPT-4 excel at high-resource languages—those with billions of words of text available on the internet—they frequently fail when tasked with low-resource languages, and particularly indigenous languages. ...

Introduction: The Voice Within Imagine trying to speak, but no sound comes out. You form the words with your mouth, your tongue moves, your jaw articulates, but the vocal cords remain silent. For millions of people suffering from speech impairments—such as those who have undergone laryngectomies—this is a daily reality. Technology has long sought to bridge this gap through Silent Speech Interfaces (SSIs). One of the most promising technologies in this field is surface electromyography (sEMG). By placing electrodes on the skin around the face and neck, sensors can detect the electrical activity of the muscles used for speech. Theoretically, if a computer can read these electrical signals, it can translate them into text. ...

The rise of Large Language Models (LLMs) like GPT-4 and Qwen has revolutionized how we write code. We can now prompt a model to generate complex algorithms, solve competitive programming problems, and scaffold entire applications. But any experienced software engineer knows that writing code is only half the battle. The other half—often the harder half—is testing it. If an AI generates a sorting algorithm, how do we know it works for every edge case? Can the AI itself generate the test cases needed to verify that code? ...

The Hidden Backbone: Why Community Notes Need Professional Fact-Checkers In the ever-evolving landscape of social media, the battle against misinformation has taken a fascinating turn. For years, platforms like Facebook and Twitter (now X) relied on partnerships with professional fact-checking organizations—groups like Snopes, PolitiFact, and Reuters—to flag false claims. However, recently, the tide has shifted toward “community moderation.” The logic seems democratic and scalable: instead of paying a small group of experts to check a massive volume of content, why not empower the users themselves to police the platform? This is the philosophy behind Community Notes on X (formerly Twitter). The idea is that the “wisdom of the crowd” can identify falsehoods faster and more effectively than a newsroom. ...

Introduction In the current landscape of Large Language Model (LLM) development, data is the new gold. But not just any data—we are specifically obsessed with Instruction Tuning (IT) data. This is the dataset that turns a raw, text-predicting base model into a helpful chatbot that can answer questions, summarize emails, and write code. A prevailing trend in recent research is “Less is More.” Studies like LIMA (Less Is More for Alignment) have suggested that you don’t need millions of instructions to train a great model; you might only need 1,000 highly curated, high-quality examples. This has triggered a gold rush to find the perfect “high-quality” dataset. Every week, a new paper claims that “Dataset A is better than Dataset B” or that a specific filtering method selects the best data. ...

Introduction When you read the phrase “Her heart was racing,” what do you understand? Depending on the context, she could be terrified of a spider, or she could be looking at the love of her life. This is the challenge of Embodied Emotion. Emotions aren’t just abstract concepts in our brains; they are physical experiences. We clench our fists in anger, our stomachs churn in disgust, and our eyes widen in surprise. In Natural Language Processing (NLP), detecting explicit emotions (e.g., “I am happy”) is a solved problem. However, detecting the subtle, physical manifestations of emotion—and correctly classifying them—remains a significant hurdle. ...

Introduction We’ve all been there: a friend says “I’m fine,” but their crossed arms, avoided eye contact, and stiff posture scream the exact opposite. As humans, a massive chunk of our communication relies on these nonverbal cues. We interpret intent, emotion, and social dynamics not just by listening to words, but by “reading the room.” For Artificial Intelligence, specifically Video Large Language Models (VideoLLMs), this is a frontier that remains largely unconquered. While models like GPT-4o or Gemini are getting remarkably good at describing what objects are in a video, understanding the emotional subtext of human movement is a different beast entirely. Human body language lacks formal rules; it is fluid, culturally dependent, and often unconscious. ...

Dyslexia is one of the most common learning disabilities, affecting an estimated 9% to 12% of the population. It is not a visual problem, nor is it related to intelligence; rather, it is a difficulty with phonological decoding—mapping sounds to letters. While the condition is lifelong, early diagnosis is the single most critical factor in ensuring a child stays on track in the educational system. The problem, however, is logistics. Standard testing batteries for dyslexia are expensive, time-consuming, and require one-on-one administration by trained specialists who are not always available in schools. This creates a bottleneck where many children slip through the cracks. ...

Introduction If you have ever taken a computer science algorithms course, you know the drill. When asked “What is the efficient sorting algorithm?”, the answer is almost reflexively “Merge Sort,” “Heap Sort,” or “Quick Sort.” Why? Because of Big O notation. We are taught that \(O(n \log n)\) is the gold standard for comparison-based sorting, while algorithms like Bubble Sort (\(O(n^2)\)) are relegated to the “never use in production” bin. ...

Introduction Imagine teaching a child to read. You wouldn’t start by handing them a complex legal contract or a page from Shakespeare. Instead, you begin with simple sentences: “The cat sat on the mat.” Once they master the basics, you gradually introduce more complex grammar, vocabulary, and sentence structures. This intuitive progression—learning the easy stuff before the hard stuff—is the foundation of Curriculum Learning (CL) in artificial intelligence. In the field of Natural Language Processing (NLP), however, we often ignore this intuition. We tend to train models by feeding them data in random batches, mixing simple phrases with incredibly complex, ambiguous sentences. ...

Imagine standing in the dense tropical forests of Costa Rica. The air is thick with humidity, and the soundscape is a chaotic symphony of insect buzzes, bird calls, wind rustling through leaves, and distant rumbles. In the middle of this acoustic storm (“the cocktail party problem”), a white-faced capuchin monkey calls out. For a human researcher, identifying which specific monkey just made that sound is an arduous task requiring years of training and intense focus. For a computer, it’s even harder. The lack of large, labeled datasets for wild animals has long been a bottleneck in bioacoustics. We have massive datasets for human speech and decent ones for bird calls, but for a specific species of Neotropical primate? The data is scarce. ...

Introduction: The Efficiency Bottleneck We are currently living in the era of the “Scaling Law.” The logic that has driven AI progress for the last few years is simple: bigger models equal better performance. Whether it’s Llama-3, Qwen2, or Mistral, increasing the parameter count consistently unlocks new capabilities in reasoning, coding, and general knowledge. However, this intelligence comes with a steep price tag: Inference Latency. Running a massive 70B or even 8B parameter model is computationally expensive. Every time you ask a chatbot a question, the model has to utilize all of its active parameters to generate a response. This leads to slow generation speeds and high operational costs. ...

Introduction Imagine you are reading a financial news headline: “Microsoft invests $10 billion in…” Before you even finish the sentence, your brain probably fills in the blank with “OpenAI.” You didn’t need to read the rest of the text because you relied on your prior knowledge of the entities involved. While this heuristic is useful for humans, it is a significant problem for Artificial Intelligence. In the field of Natural Language Processing (NLP), this phenomenon is known as Entity Bias. Models like BERT or RoBERTa often memorize connections between specific entities (e.g., “Microsoft” and “invest”) rather than understanding the context of the sentence. If the sentence actually read “Microsoft sues OpenAI,” a biased model might still predict an “investment” relationship simply because it over-relies on the names. ...

Imagine you are a carpenter building tables. You have a ruler to measure the length of your work. But this ruler has a strange property: when you measure a table made of oak, an inch is exactly 2.54 centimeters. But when you measure a table made of pine, the ruler magically shrinks, and an “inch” becomes only 2 centimeters. As a result, your pine tables receive inflated measurements, while your oak tables are penalized. ...

Introduction In the current landscape of Artificial Intelligence, data is the new oil, but the wells are running dry. From the early days of BERT to the massive scale of GPT-4, the growth of Language Models (LMs) has been fueled by an exponential increase in training data. However, we are approaching a critical bottleneck: high-quality, human-annotated data is expensive, slow to produce, and difficult to scale for specialized tasks. Faced with this “data hunger,” researchers and engineers have turned to a promising alternative: Synthetic Data. If modern Large Language Models (LLMs) are so smart, why not ask them to generate the training data for the next generation of models? It sounds like the perfect perpetual motion machine—AI teaching AI, eliminating the need for costly human labor. ...

Imagine you show a child a red apple. They learn what an “apple” is. Later, you show them a green apple, or perhaps a plastic toy apple painted blue. The child immediately recognizes it as an apple because they understand its shape and structure, not just its color or texture. Now, try the same experiment with a standard computer vision model. If trained only on red apples, many models will fail spectacularly when presented with a blue one. Why? Because deep neural networks are notoriously lazy: they often cheat by memorizing textures (like the specific shiny red skin) rather than learning the underlying geometry of the object. ...

Introduction In the rapidly evolving world of Computer Vision, there is a prevailing tendency to solve complex problems by adding complexity to architectures. When the Vision Transformer (ViT) burst onto the scene, it revolutionized image classification. However, when researchers tried to apply it to more granular tasks like image segmentation—where the goal is to classify every pixel—the consensus was that the “plain” ViT wasn’t enough. To bridge the gap, the field developed a standard recipe: take a ViT, attach a heavy “adapter” to extract multi-scale features (mimicking Convolutional Neural Networks), add a “pixel decoder” to fuse these features, and finally, cap it off with a complex “Transformer decoder” to generate masks. State-of-the-art models like Mask2Former follow this pattern, becoming powerful but architecturally convoluted and computationally heavy. ...

Introduction In the rapidly evolving landscape of Artificial Intelligence, Large Vision-Language Models (LVLMs) like LLaVA, GPT-4V, and DeepSeek-VL have become the superstars of multimodal understanding. These models possess an uncanny ability to describe complex scenes, answer questions about images, and even engage in reasoning tasks that were previously thought impossible. However, there has been a persistent gap in their capabilities. While an LVLM can eloquently describe a “red car parked next to a fire hydrant,” asking it to pinpoint the exact pixel coordinates of that car often results in failure or requires significant modifications to the model. This task—identifying the specific region in an image that corresponds to a text description—is known as Visual Grounding. ...

Introduction How do you understand the three-dimensional structure of the world? You don’t walk around with a ruler and a protractor, measuring the precise coordinates of every object you see. You don’t rely on “gold-standard” 3D mesh data implanted in your brain. Instead, you observe. You move your head, walk around a statue, or drive down a street. Your brain stitches these continuous 2D observations into a coherent 3D model. ...

We live in an era where Multimodal Large Language Models (MLLMs) like GPT-4o and Gemini can describe a photo of a cat on a couch with poetic detail. They can explain memes, read charts, and even help fix your coding errors based on a screenshot. But what happens when you ask these same models to look at the world from 20,000 feet up? Imagine asking an AI to analyze a satellite image of a sprawling port city. You don’t just want to know “is this a city?” You want to know: How many ships are docked? Is that traffic jam near the bridge caused by an accident? What is the safest route for a truck to get from the warehouse to the pier? ...