Multimodal Continual Instruction Tuning aims to continually enhance Large Vision Language Models (LVLMs) by learning from new data without forgetting previously acquired knowledge. Mixture of Experts (MoE) architectures naturally facilitate this by incrementally adding new experts and expanding routers while keeping the existing ones frozen. However, despite expert isolation, MoE-based continual learners still suffer from forgetting due to routing-drift: old-task tokens become mistakenly attracted to newly added experts, degrading performance on prior tasks. We analyze the failure mode […]

Ver mais

arXiv:2604.01361v1 Announce Type: new Abstract: This paper presents a new method for the zero-shot open-vocabulary semantic segmentation (OVSS) of 3D automotive lidar data. To circumvent the recognized image-text modality gap that is intrinsic to approaches based on Vision Language Models (VLMs) such as CLIP, our method relies instead on image generation from text, to create prototype images. Given a 3D network distilled from a 2D Vision Foundation Model (VFM), we then label a point cloud by matching 3D […]

Ver mais

arXiv:2602.13214v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in interactive environments requiring strategic decision-making, yet systematic evaluation of these capabilities remains challenging. Existing benchmarks for LLMs primarily assess static reasoning through isolated tasks and fail to capture dynamic strategic abilities. Recent game-based evaluations employ LLM-vs-LLM tournaments that produce relative rankings dependent on transient model pools, incurring quadratic computational costs and lacking stable performance anchors for longitudinal tracking. The central challenge is establishing a scalable […]

Ver mais

arXiv:2604.09680v1 Announce Type: new Abstract: Today’s 5G and NextG wireless networks are moving toward using the coordinated multi-point (CoMP) transmission and reception technique, where a client can be simultaneously served by multiple base stations (BSs) for better communication performance. However, traditional hierarchical federated learning (HFL) architectures impose the constraint that each client can be associated with only one edge server (ES) at a time. If we keep using the traditional HFL architectures in modern hierarchical networks for model […]

Ver mais

RL sounds like a lot of fun from the outside. “AI for training robots to learn from experience”, sounds good. But when you dive in, it can be really frustrating and overwhelming to learn. Rather than being a single clear algorithm, there are many named algorithms: Actor Critic, A2C, PPO, DDPG, TD3, SAC etc.. it turns out that every named algorithm is the result of a research paper. But generally, these are not distinctive algorithms. For instance, if […]

Ver mais

arXiv:2601.07894v1 Announce Type: new Abstract: Masked diffusion models (MDMs), which leverage bidirectional attention and a denoising process, are narrowing the performance gap with autoregressive models (ARMs). However, their internal attention mechanisms remain under-explored. This paper investigates the attention behaviors in MDMs, revealing the phenomenon of Attention Floating. Unlike ARMs, where attention converges to a fixed sink, MDMs exhibit dynamic, dispersed attention anchors that shift across denoising steps and layers. Further analysis reveals its Shallow Structure-Aware, Deep Content-Focused attention […]

Ver mais

arXiv:2510.13868v2 Announce Type: replace-cross Abstract: We propose textit{DeepMartingale}, a deep-learning framework for the dual formulation of discrete-monitoring optimal stopping problems under continuous-time models. Leveraging a martingale representation, our method implements a emph{pure-dual} procedure that directly optimizes over a parameterized class of martingales, producing computable and tight emph{dual upper bounds} for the value function in high-dimensional settings without requiring any primal information or Snell-envelope approximation. We prove convergence of the resulting upper bounds under mild assumptions for both first- […]

Ver mais

arXiv:2502.10510v3 Announce Type: replace-cross Abstract: Modern machine learning pipelines are increasingly combining and mixing data from diverse and disparate sources, e.g., pre-training large language models. Yet, finding the optimal data mixture is a challenging and open problem. We formalize this data mixing problem as a bi-level objective: the best mixture is the one that would lead to the best model for a downstream objective. Unfortunately, this objective is generally intractable. In this paper, we make the observation that […]

Ver mais

Table of Links Abstract and 1. Introduction Related Work and Background Analysis 3.1 Limitations about Existing ReLUficatio 3.2 dReLU Are Neurons in Expert still Sparsely Activated? dReLU Sparsification Experiments Results 6.1 Downstream Tasks Performance 6.2 Sparsity of Sparsified Models Practical Inference Speedup Evaluation 7.1 Experiments Setting 7.2 Pure CPU Inference and 7.3 Hybrid GPU-CPU Inference 7.4 Deploy LLMs on mobile phones Conclusion and References A. Appendix / supplemental material B. Limitation C. Broader Impact 3 Analysis 3.1 Limitations […]

Ver mais