arXiv:2602.21222v1 Announce Type: new Abstract: Parameter efficient fine tuning methods like LoRA have enabled task specific adaptation of large language models, but efficiently composing multiple specialized adapters for unseen tasks remains challenging. We present a novel framework for dynamic LoRA adapter composition that leverages similarity retrieval in vector databases to enable zero-shot generalization across diverse NLP tasks. Our approach constructs a task-aware vector database by embedding training examples from 22 datasets spanning commonsense reasoning, question answering, natural language […]

Ver mais

In this work, we propose a notion of practical learnability grounded in finite sample settings, and develop a conjugate learning theoretical framework based on convex conjugate duality to characterize this learnability property. Building on this foundation, we demonstrate that training deep neural networks (DNNs) with mini-batch stochastic gradient descent (SGD) achieves global optima of empirical risk by jointly controlling the extreme eigenvalues of a structure matrix and the gradient energy, and we establish a corresponding convergence theorem. We […]

Ver mais

arXiv:2602.22254v1 Announce Type: new Abstract: We introduce Causal Computational Asymmetry (CCA), a principle for causal direction identification based on optimization dynamics in which one neural network is trained to predict $Y$ from $X$ and another to predict $X$ from $Y$, and the direction that converges faster is inferred to be causal. Under the additive noise model $Y = f(X) + varepsilon$ with $varepsilon perp X$ and $f$ nonlinear and injective, we establish a formal asymmetry: in the reverse […]

Ver mais

I’ve never been good at shell scripting. I’d much rather write scripts in a general purpose language like Python. But occasionally a shell script can do something so simply that it’s worth writing a shell script. Sometimes a shell scripting feature is terse and cryptic precisely because it solves a common problem succinctly. One example of this is working with file extensions. For example, maybe you have a script that takes a source file name like foo.java and […]

Ver mais

arXiv:2111.09266v5 Announce Type: replace-cross Abstract: Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates in an active learning context, with a training objective that makes them approximately sample in proportion to a given reward function. In this paper, we show a number of additional theoretical properties of GFlowNets. They can be used to estimate joint probability distributions and the corresponding marginal distributions where some variables are unspecified and, of particular […]

Ver mais

arXiv:2602.07215v1 Announce Type: new Abstract: Generative AI (GenAI) has transformed applications in natural language processing and content creation, yet centralized inference remains hindered by high latency, limited customizability, and privacy concerns. Deploying large models (LMs) in mobile edge networks emerges as a promising solution. However, it also poses new challenges, including heterogeneous multi-modal LMs with diverse resource demands and inference speeds, varied prompt/output modalities that complicate orchestration, and resource-limited infrastructure ill-suited for concurrent LM execution. In response, we […]

Ver mais

Why standard diffusion models fail at B2B — and how we built a two-stage “Architect-Builder” pipeline to fix it. The “Slot Machine” Problem: Why AI Art is Bad for Business In the generative AI gold rush, many products fall into the same trap: they rely on the “stochastic luck” of diffusion models. For a consumer app, a “pretty” result is enough. For a B2B tool in the hair styling industry — where hairss operates — visual inconsistency is […]

Ver mais

Topological deep learning has emerged for modeling higher-order relational structures beyond pairwise interactions that standard graph neural networks fail to capture. Although combinatorial complexes offer a unified topological framework, most existing topological deep learning methods rely on local message passing via attention mechanisms, which incur quadratic complexity and remain low-dimensional, limiting scalability and rank-aware information aggregation in higher-order complexes.We propose Combinatorial Complex Mamba (CCMamba), the first unified mamba-based neural framework for learning on combinatorial complexes. CCMamba reformulates message […]

Ver mais