7 papers
TextNCA: Neural Cellular Automata for Language Modeling via Hierarchical Local Attention
Avni Mittal, Avinash Anand, Ashutosh Kumar +7
Can a strictly local, iterated, weight-shared computation primitive support language modelling, and which of those three properties actually drives the model's behaviour? We define…
FORGE: Fused On-Register Gradient Elimination for Memory-Efficient LLM Training
Dikshant Kukreja, Kritarth Prasad, Avinash Anand +6
Reverse-mode differentiation computes every weight gradient, writes it to memory, and only then lets the optimizer read it back. This two-phase schedule sets the memory ceiling of…
The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm
Karan Goyal
The rapid proliferation of Vision-Language Models (VLMs) is often framed as enabling unified multimodal knowledge discovery but rests on an under-examined assumption: that current…
Better and Worse with Scale: How Contextual Entrainment Diverges with Model Size
Dikshant Kukreja, Kshitij Sah, Gautam Gupta +5
Larger language models become simultaneously better and worse at handling contextual information -- better at ignoring false claims, worse at ignoring irrelevant tokens. We formali…
Public Profile Matters: A Scalable Integrated Approach to Recommend Citations in the Wild
Karan Goyal, Dikshant Kukreja, Vikram Goyal +1
Proper citation of relevant literature is essential for contextualising and validating scientific contributions. While current citation recommendation systems leverage local and gl…
CAGE: Bridging the Accuracy-Aesthetics Gap in Educational Diagrams via Code-Anchored Generative Enhancement
Dikshant Kukreja, Kshitij Sah, Karan Goyal +2
Educational diagrams -- labeled illustrations of biological processes, chemical structures, physical systems, and mathematical concepts -- are essential cognitive tools in K-12 ins…