arXiv:2506.00486v4 Announce Type: replace-cross Abstract: Despite rapid progress in large language models (LLMs), the statistical structure of their weights, activations, and gradients-and its implications for initialization, training dynamics, and efficiency-remains largely unexplored. We empirically show that these quantities in LLMs are well modeled by generalized Gaussian (GG) distributions, and introduce a unified, end-to-end optimization framework grounded in this observation. Our contributions are threefold: (1) a GG-based initialization that aligns with trained model statistics, accelerating convergence and improving accuracy; […]

Ver mais

arXiv:2602.03975v1 Announce Type: new Abstract: Test-time computation has become a primary driver of progress in large language model (LLM) reasoning, but it is increasingly bottlenecked by expensive verification. In many reasoning systems, a large fraction of verifier calls are spent on redundant or unpromising intermediate hypotheses. We study reasoning under a emph{verification-cost-limited} setting and ask how verification effort should be allocated across intermediate states. We propose a state-level selective verification framework that combines (i) deterministic feasibility gating over […]

Ver mais

Machine learning is at the heart of managing the real-world problems associated with massive data. With the success of neural networks on such large-scale problems, more research in machine learning is being conducted now than ever before. This dissertation focuses on three different projects rooted in mathematical theory for machine learning applications. The first project deals with supervised learning and manifold learning. In theory, one of the main problems in supervised learning is that of function approximation: that […]

Ver mais

arXiv:2601.20903v1 Announce Type: new Abstract: Multi-turn jailbreak attacks have emerged as a critical threat to Large Language Models (LLMs), bypassing safety mechanisms by progressively constructing adversarial contexts from scratch and incrementally refining prompts. However, existing methods suffer from the inefficiency of incremental context construction that requires step-by-step LLM interaction, and often stagnate in suboptimal regions due to surface-level optimization. In this paper, we characterize the Intent-Context Coupling phenomenon, revealing that LLM safety constraints are significantly relaxed when a […]

Ver mais

arXiv:2602.12342v1 Announce Type: new Abstract: How can we train agents to navigate uncertainty over long horizons? In this work, we propose {Delta}Belief-RL, which leverages a language model’s own intrinsic beliefs to reward intermediate progress. Our method utilizes the change in the probability an agent assigns to the target solution for credit assignment. By training on synthetic interaction data, {Delta}Belief-RL teaches information-seeking capabilities that consistently outperform purely outcome-based rewards for Reinforcement Learning, with improvements generalizing to out-of-distribution applications ranging […]

Ver mais

arXiv:2305.04979v2 Announce Type: replace-cross Abstract: We propose a novel hierarchical Bayesian approach to Federated Learning (FL), where our model reasonably describes the generative process of clients’ local data via hierarchical Bayesian modeling: constituting random variables of local models for clients that are governed by a higher-level global variate. Interestingly, the variational inference in our Bayesian model leads to an optimisation problem whose block-coordinate descent solution becomes a distributed algorithm that is separable over clients and allows them not […]

Ver mais

arXiv:2602.15918v1 Announce Type: new Abstract: Benchmarking spatial reasoning in multimodal large language models (MLLMs) has attracted growing interest in computer vision due to its importance for embodied AI and other agentic systems that require precise interaction with the physical world. However, spatial reasoning on Earth imagery has lagged behind, as it uniquely involves grounding objects in georeferenced images and quantitatively reasoning about distances, directions, and topological relations using both visual cues and vector geometry coordinates (e.g., 2D bounding […]

Ver mais

Hi! I am trying to explore and learn some RL algorithms and implement them in Gym’s Car Racing environment ( https://gymnasium.farama.org/environments/box2d/car_racing/ ). Instead of using the image on the screen for my state, I measure the distance from the car to the edge of the track at 5 points (90º left, 45º left, forwards, 45º right, 90º right), along with the car’s current speed, and pass that as my state. I also give a fixed -1 reward if […]

Ver mais

Machine learning approaches for fringe projection profilometry (FPP) are hindered by the lack of large, diverse datasets and comprehensive benchmarking protocols. This paper introduces the first open-source, photorealistic synthetic dataset for FPP, generated using NVIDIA Isaac Sim with 15,600 fringe images and 300 depth reconstructions across 50 diverse objects. We benchmark four neural network architectures (UNet, Hformer, ResUNet, Pix2Pix) on single-shot depth reconstruction, revealing that all models achieve similar performance (58-77 mm RMSE) despite substantial architectural differences. Our […]

Ver mais

arXiv:2602.22352v1 Announce Type: new Abstract: With the continuous growth of neural network scales, low-precision quantization is widely used in edge accelerators. Classic multi-threshold activation hardware requires 2^n thresholds for n-bit outputs, causing a rapid increase in hardware cost as precision increases. We propose a reconfigurable activation hardware, GRAU, based on piecewise linear fitting, where the segment slopes are approximated by powers of two. Our design requires only basic comparators and 1-bit right shifters, supporting mixed-precision quantization and nonlinear […]

Ver mais