The bifurcation of generative modeling into autoregressive approaches for discrete data (text) and diffusion approaches for continuous data (images) hinders the...
What I initially believed Before digging in, I implicitly believed a few things: - If an attention head consistently attends to a specific token, that token is...
The field of emergent communication within multi-agent systems examines how autonomous agents can independently develop communication strategies, without explic...
Spatio-temporal reasoning in time series involves the explicit synthesis of temporal dynamics, spatial dependencies, and textual context. This capability is vit...
Background: Reporting and Data Systems (RADS) standardize radiology risk communication but automated RADS assignment from narrative reports is challenging becau...
Student mistakes in mathematics are often systematic: a learner applies a coherent but wrong procedure and repeats it across contexts. We introduce MalruleLib, ...
In enterprise search, building high-quality datasets at scale remains a central challenge due to the difficulty of acquiring labeled data. To resolve this chall...
While Large Language Models (LLMs) have demonstrated significant potential in natural language processing , complex general-purpose reasoning requiring multi-st...
Diffusion language models (DLMs) have shown strong potential for general natural language tasks with in-context examples. However, due to the bidirectional atte...
Hate speech detection on social media faces challenges in both accuracy and explainability, especially for underexplored Indic languages. We propose a novel exp...
The hallmark of human intelligence is the ability to master new skills through Constructive Episodic Simulation-retrieving past experiences to synthesize soluti...
Machine unlearning aims to forget sensitive knowledge from Large Language Models (LLMs) while maintaining general utility. However, existing approaches typicall...
