Neurochaos Learning (NL) has shown promise in recent times over traditional deep learning due to its two key features: ability to learn from small sized training samples, and low compute requirements. In prior work, NL has been implemented and extensively tested on separable and time series data, and demonstrated its superior performance on both classification and regression tasks. In this paper, we investigate the next step in NL, viz., applying NL to linked data, in particular, data that […]

Ver mais

Recent developments have shown that Muon-type optimizers based on linear minimization oracles (LMOs) over non-Euclidean norm balls have the potential to get superior practical performance than Adam-type methods in the training of large language models. Since large-scale neural networks are trained across massive machines, communication cost becomes the bottleneck. To address this bottleneck, we investigate Gluon, which is an extension of Muon under the more general layer-wise $(L^0, L^1)$-smooth setting, with both unbiased and contraction compressors. In order […]

Ver mais

arXiv:2601.05384v1 Announce Type: new Abstract: As AI agents increasingly operate in multi-agent environments, understanding their collective behavior becomes critical for predicting the dynamics of artificial societies. This study examines conformity, the tendency to align with group opinions under social pressure, in large multimodal language models functioning as AI agents. By adapting classic visual experiments from social psychology, we investigate how AI agents respond to group influence as social actors. Our experiments reveal that AI agents exhibit a systematic […]

Ver mais

arXiv:2604.15448v1 Announce Type: new Abstract: Foundational optimization embeddings have recently emerged as powerful pre-trained representations for mixed-integer programming (MIP) problems. These embeddings were shown to enable cross-domain transfer and reduce reliance on solver-generated labels. In this work, we investigate whether such representations generalize beyond optimization to decision problems, focusing on Boolean satisfiability (SAT). We adapt the foundational optimization architecture to SAT by mapping CNF formulas into the same bipartite constraint-variable graph representation used for MIPs. This allows direct […]

Ver mais

arXiv:2509.09353v2 Announce Type: replace Abstract: Low-degree polynomials have emerged as a powerful paradigm for providing evidence of statistical-computational gaps across a variety of high-dimensional statistical models [Wein25]. For detection problems — where the goal is to test a planted distribution $mathbb{P}’$ against a null distribution $mathbb{P}$ with independent components — the standard approach is to bound the advantage using an $mathbb{L}^2(mathbb{P})$-orthonormal family of polynomials. However, this method breaks down for estimation tasks or more complex testing problems where […]

Ver mais

Hey everyone, I’m fascinated by RL for LLMs. I have some SFT experience but none with RL, and I’d like to start experimenting with DPO. Some context: Over time I’ve built a framework for building LLM agents that I use internally at the company where I work. It started as na side project but evolved quite a bit, i recently added a tracer and an MCP server for Claude on top of it. What does this mean in […]

Ver mais

Offline reinforcement learning (RL) optimizes policies from a previously collected static dataset and is an important branch of RL. A popular and promising approach is to regularize actor-critic methods with behavior cloning (BC), which yields realistic policies and mitigates bias from out-of-distribution actions, but can impose an often-overlooked performance ceiling: when dataset actions are suboptimal, indiscriminate imitation structurally prevents the actor from fully exploiting high-value regions suggested by the critic, especially in later training when imitation is already […]

Ver mais

Despite deep learning models running well-defined mathematical functions, we lack a formal mathematical framework for describing model architectures. Ad-hoc notation, diagrams, and pseudocode poorly handle nonlinear broadcasting and the relationship between individual components and composed models. This paper introduces a categorical framework for deep learning models that formalizes broadcasting through the novel axis-stride and array-broadcasted categories. This allows the mathematical function underlying architectures to be precisely expressed and manipulated in a compositional manner. These mathematical definitions are translated […]

Ver mais

arXiv:2604.18610v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress but incur substantial computational overhead and energy consumption during inference, limiting deployment in resource-constrained environments. Spiking Neural Networks (SNNs), with their sparse event-driven computation, offer inherent energy efficiency advantages on neuromorphic hardware, yet extending them to MLLMs faces two key challenges: heterogeneous modalities make uniform spike encoding insufficient, and high-resolution image inputs amplify timestep unfolding overhead. We propose SpikeMLLM, the first spike-based framework for […]

Ver mais