Papers

The integration of Large Language Models (LLMs) into the biomedical domain holds immense promise, from assisting in complex diagnoses to automating clinical note-taking. However, a significant barrier stands in the way of widespread adoption: the “resource-privacy-performance” trilemma. On one hand, we have massive Black-Box LLMs (like GPT-4) that offer state-of-the-art reasoning but come with high costs and severe privacy risks when patient data is involved. On the other hand, we have White-Box LLMs (like LLaMA-2) that can be run locally and privately, but often struggle to match the reasoning capabilities of their larger counterparts, even after expensive fine-tuning. ...

Introduction We have reached a point in the evolution of Artificial Intelligence where machines can generate text that is grammatically perfect, stylistically consistent, and undeniably coherent. If you ask GPT-4 to write a sonnet about a toaster, it will do so with impressive rhyme and meter. But there is a frontier that has remained elusive, a quality that separates a technical manual from a heartbreaking novel: Psychological Depth. Evaluations of Large Language Models (LLMs) have traditionally focused on objective metrics. We measure perplexity, distinct-n-grams, and discourse coherence. We check for toxicity and bias. While indispensable, these metrics treat text as data. They do not account for the reader. They cannot tell us if a story evokes empathy, if it makes your heart race, or if the characters feel like genuine human beings rather than cardboard cutouts. ...

In the world of Large Language Models (LLMs) and Information Retrieval (IR), bigger has almost always meant better. High-dimensional embeddings—those long vectors of numbers representing the semantic meaning of text—capture subtle nuances that smaller vectors miss. A 3,072-dimensional vector from OpenAI usually understands your query better than a 256-dimensional one. But “bigger” comes with a steep price tag. Storing millions of high-dimensional vectors requires massive amounts of memory. Searching through them (vector search) creates high latency and computational costs. Engineers are often stuck in a dilemma: choose high accuracy and burn through the budget, or choose efficiency and accept worse search results. ...

Introduction In the rapidly evolving landscape of Artificial Intelligence, we have become accustomed to headlines declaring that Large Language Models (LLMs) have conquered yet another human milestone. We see models acing the Bar Exam, performing at graduate levels in physics, and solving complex code challenges. If you look at popular leaderboards, it seems we are approaching a saturation point where AI capabilities match or exceed specialized human performance. But there is a catch. ...

Imagine watching a soccer match where the commentator screams “Goal!” two minutes after the ball has already hit the net. It would be disorienting, annoying, and largely useless. Yet, this is the precise problem plaguing Artificial Intelligence when we try to teach it to understand sports. For years, researchers have been trying to build systems that can automatically narrate sports videos. The potential is immense: from automated highlights to assisting visually impaired fans. However, current models often fail to sound professional or accurate. ...

Introduction Imagine a student preparing for a difficult mathematics exam. They don’t just memorize formulas; they work through practice problems. When they solve a problem correctly, they remember the logic they used. Later, when they face a similar but new problem, they recall that successful logic to guide them. This process—accumulating experiences, filtering out the mistakes, and recalling the most relevant and complex solutions—is fundamental to human learning. However, standard Large Language Models (LLMs) often lack this dynamic “experiential” capability in their standard deployment. They are typically static. You prompt them, they answer, and the interaction ends. If they solve a problem brilliantly, that “thought process” usually evaporates once the session closes. ...

The capabilities of Large Language Models (LLMs) like GPT-4 and LLaMA have revolutionized artificial intelligence. However, if you have ever watched an LLM generate a response, you have likely noticed a fundamental bottleneck: the text appears one word at a time, like a slow typist. This sluggishness is due to the Auto-Regressive (AR) decoding paradigm. To generate the 100th token, the model strictly needs the previous 99 tokens. This sequential dependency prevents parallel processing during generation, leaving powerful GPUs idling while they wait for the next token to be decided. ...

Imagine you are analyzing the novel Aladdin. You want to track every time the text refers to the protagonist, whether by his name (“Aladdin”), a nominal phrase (“the boy”), or a pronoun (“he”). In Natural Language Processing (NLP), this is classically handled by Coreference Resolution (CR). The goal of CR is to find every mention in a text and cluster them together based on which entity they refer to. It sounds straightforward, but in practice, CR is notoriously difficult. Models trained on news articles often fail spectacularly when applied to literature or medical texts. Why? because they get bogged down trying to resolve everything, including insignificant background characters or abstract concepts, often disagreeing on what even counts as a “mention.” ...

Introduction Imagine you are looking at a crowded photograph of a street scene. A friend stands beside you and says, “Look at the guy in the yellow shirt standing near the bike.” Instantly, your brain processes the language, scans the image, filters out the “guys in blue shirts” and “guys near cars,” and locks onto the specific target. In computer vision, this task is known as Referring Expression Comprehension (REC). The goal is to ground a specific region in an image based on a natural language description. While this sounds intuitive to humans, it is a complex challenge for AI. It requires a model to possess strong visual perception, deep linguistic understanding, and—most importantly—the ability to align these two modalities perfectly. ...

Language is a strange thing. If you speak English, the word “Love” is a familiar sequence of four letters. If you speak Greek, “αγάπη” carries the same emotional weight but looks completely different. If you speak Chinese, “爱” is a distinct logogram. ...

Introduction In the world of Information Retrieval (IR), we are constantly balancing a difficult trade-off: accuracy versus speed. We want our search engines to understand the nuance of human language like a massive Large Language Model (LLM), but we need them to return results in milliseconds like a simple keyword search. Dense Passage Retrieval (DPR) has emerged as a powerful solution, using deep learning to represent queries and documents as vectors. However, the most accurate DPR models are often massive, computationally expensive, and slow to deploy. To solve this, researchers turn to Knowledge Distillation (KD)—a technique where a small, fast “student” model learns to mimic a large, slow “teacher” model. ...

Introduction We are currently living in the “golden age” of Large Language Models (LLMs). From drafting emails to generating code snippets, models like GPT-4 and Llama-2 have integrated themselves into our daily workflows. When we benchmark these models, however, we often treat them like search engines: we ask a single question, get a single answer, and grade the result. But is this how we actually use AI? In the real world, interaction is rarely a one-shot event. We chat. We ask for revisions. We change the topic slightly, then circle back to an earlier point. We ask the model to “remember what I said three messages ago.” This is the domain of multi-turn interaction, and it is a significantly harder challenge for an AI than answering a standalone query. ...

Introduction Imagine you are teaching a robot how to navigate a kitchen. On day one, you teach it how to make a salad. It learns a valuable lesson: “Use a bowl to hold the ingredients.” On day two, you ask the robot to water a plant. The robot, eager to apply its past knowledge, remembers the concept of a “bowl” and the action “fill with water.” However, because its memory is cluttered, it might erroneously try to “slice” the water or mix the plant with dressing because it associates bowls with cooking. ...

Introduction In the world of Artificial Intelligence, Knowledge Graphs (KGs) are the unsung heroes. They power the sidebar on your Google Search, drive product recommendations on Amazon, and help complex systems understand that “Paris” is the capital of “France.” To make these graphs useful for machine learning, we use Knowledge Graph Embedding (KGE) models. These models translate entities (like “Paris”) and relations (like “is capital of”) into mathematical vectors and matrices. ...

Have you ever noticed how rigid most chatbots feel? You ask about the weather, and they tell you the forecast. You ask about a restaurant, and they give you a menu. But if you try to naturally segue from that restaurant to the history of the cuisine, and then perhaps to a famous chef who cooks that cuisine, the bot often stumbles. It loses context or treats the new topic as a completely isolated query. ...

Introduction We are living in the era of massive artificial intelligence. In recent years, deep learning models—particularly Transformers—have shattered records in computer vision and natural language processing. We have moved beyond simple image classifiers to complex multimodal systems capable of understanding video, audio, and text simultaneously. However, this capability comes at a steep price. Between 2012 and 2020, the computational requirements for state-of-the-art machine learning applications increased by a staggering factor of 1,000,000. While hardware has improved, it hasn’t kept pace with this exponential growth. This creates a massive bottleneck for inference serving—the process of actually running these models in production to generate predictions for users. ...

Introduction In the rapidly evolving world of Artificial Intelligence, “Open Source” has become a buzzword. From Large Language Models (LLMs) to Speech Foundation Models (SFMs), developers and researchers are flooded with new releases claiming to be open. But if you scratch beneath the surface, a complex problem emerges: Open Washing. Many models release their weights (the trained parameters) but keep their training data and code proprietary. Even when data is released, it often comes with restrictive licenses—such as “Non-Commercial” or “No-Derivatives”—which strictly violates the definition of Open Source AI. For undergraduate and master’s students entering the field, this distinction is critical. You cannot build a truly open, community-driven, or commercial application if the foundation you are building on is legally shaky. ...

Imagine chatting with a sophisticated AI. You ask, “What did you do this weekend?” and it replies, “I went hiking with my dog.” Ten minutes later, you mention you love nature, and it replies, “I hate the outdoors, I prefer video games.” The illusion breaks. The personality—or persona—is inconsistent. Building chatbots that maintain a consistent, engaging personality is one of the “holy grails” of Natural Language Processing (NLP). traditionally, this is done by explicitly feeding the model a “role profile” (e.g., Name: Alex, Hobby: Hiking, Pet: Dog) every time it generates a response. But in the real world, we often don’t have access to these explicit profiles due to data scarcity or privacy concerns. We only have the dialogue history—the breadcrumbs of personality left behind in previous conversations. ...

Introduction Imagine scrolling through social media and seeing a photo of a chaotic, messy room with the caption, “Living my best life.” As a human, you immediately recognize the sarcasm. The image (mess) and the text (“best life”) contradict each other, and that contradiction creates the meaning. Now, consider how a standard Multimodal AI sees this. It processes the image, processes the text, and tries to align them. It might see “mess” and “best life” and simply get confused because the semantic content doesn’t overlap. This highlights a critical limitation in current Vision-Language Models (VLMs): they are excellent at identifying when images and text say the same thing (redundancy), but they struggle when the meaning emerges from the interaction between the two (synergy), such as in sarcasm or humor. ...

Introduction: The “Pink Elephant” in the Room Imagine you are trying to tell a friend that you were incredibly drunk last night. If you are speaking English, you might say you were “seeing pink elephants.” Now, imagine feeding that sentence into a translation engine to communicate with a friend in China. If the AI translates it literally, your Chinese friend might be confused about why you were at a zoo. In Chinese culture, a common metaphorical equivalent for being heavily drunk is “collapsed like quagmire” (烂醉如泥). ...