arXiv:2410.13341v3 Announce Type: replace-cross Abstract: High quality annotations are increasingly a bottleneck in the explosively growing machine learning ecosystem. Scalable evaluation methods that avoid costly annotation have therefore become an important research ambition. Many hope to use strong existing models in lieu of costly labels to provide cheap model evaluations. Unfortunately, this method of using models as judges introduces biases, such as self-preferencing, that can distort model comparisons. An emerging family of debiasing tools promises to fix these […]

Ver mais

arXiv:2602.11186v1 Announce Type: new Abstract: The integration of Generative AI (GenAI) into Consumer Electronics (CE)–from AI-powered assistants in wearables to generative planning in autonomous Uncrewed Aerial Vehicles (UAVs)–has revolutionized user experiences. However, these GenAI applications impose immense computational burdens on edge hardware, leaving strictly limited resources for fundamental security tasks like Global Navigation Satellite System (GNSS) signal protection. Furthermore, training robust classifiers for such devices is hindered by the scarcity of real-world interference data. To address the dual […]

Ver mais

arXiv:2408.06710v3 Announce Type: replace-cross Abstract: Gaussian Process Latent Variable Models (GPLVMs) have become increasingly popular for unsupervised tasks such as dimensionality reduction and missing data recovery due to their flexibility and non-linear nature. An importance-weighted version of the Bayesian GPLVMs has been proposed to obtain a tighter variational bound. However, this version of the approach is primarily limited to analyzing simple data structures, as the generation of an effective proposal distribution can become quite challenging in high-dimensional spaces […]

Ver mais

arXiv:2602.21220v1 Announce Type: new Abstract: We present a memory system for AI agents that treats stored information as continuous fields governed by partial differential equations rather than discrete entries in a database. The approach draws from classical field theory: memories diffuse through semantic space, decay thermodynamically based on importance, and interact through field coupling in multi-agent scenarios. We evaluate the system on two established long-context benchmarks: LoCoMo (ACL 2024) with 300-turn conversations across 35 sessions, and LongMemEval (ICLR […]

Ver mais

arXiv:2511.19566v2 Announce Type: replace-cross Abstract: Open weight models, which are ubiquitous, rarely provide access to their training data or loss function. This makes modifying such models for tasks such as pruning or unlearning, which are constrained by this unavailability, an active area of research. Existing techniques typically require gradients or ground-truth labels, rendering them infeasible in settings with limited computational resources. In this work, we investigate the fundamental question of identifying components that are critical to the model’s […]

Ver mais

arXiv:2603.02224v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has emerged as a parameter-efficient approach for adapting large pre-trained models, yet its behavior under continual learning remains poorly understood. We present a geometric theory characterizing catastrophic forgetting in LoRA through the lens of gradient subspace interactions. Our central finding is that forgetting is governed by a simple geometric law: $mathcal{F} = alpha(1 – cos^2theta_{min}) + beta$, where $theta_{min}$ is the minimum principal angle between task gradient subspaces. This formulation […]

Ver mais

arXiv:2604.16979v1 Announce Type: new Abstract: High-quality and diverse multimodal data are essential for improving vision-language models (VLMs), yet existing datasets often contain noisy, redundant, and poorly aligned samples. To address these problems, data filtering is commonly used to enhance the efficiency and performance of multimodal learning, but it introduces extra computational cost because filtering models are usually trained on the same data they are meant to screen. To reduce this cost, we study DOSE, which explores whether off-the-shelf […]

Ver mais

We prove that the set ( T=Bigl{ninmathbb{N}: exists p,qinmathbb{N};Bigl((2n=(p+q)(p+q+1)+2q);wedge ) ( forall (x_0,ldots,x_p)inmathbb{N}^{p+1};exists (y_0,ldots,y_p)in{0,ldots,q}^{p+1} ) ( bigl((forall kin{0,ldots,p};(1=x_k Rightarrow 1=y_k));wedge ) ( (forall i,j,kin{0,ldots,p};(x_i+x_j=x_k Rightarrow y_i+y_j=y_k));wedge ) ( (forall i,j,kin{0,ldots,p};(x_icdot x_j=x_k Rightarrow y_icdot y_j=y_k))bigr)Bigr)Bigr} ) is not recursively enumerable. By using Gödel’s ( beta ) function, we prove that the formula that defines the set T can be easily translated into a first-order formula which uses only + and ( cdot ). The same properties has the set […]

Ver mais

arXiv:2603.26675v1 Announce Type: new Abstract: Block diffusion enables efficient parallel refinement in diffusion language models, but its decoding behavior depends critically on block size. Existing block-sizing strategies rely on fixed rules or heuristic signals and do not account for the dependency geometry that determines which tokens can be safely refined together. This motivates a geometry view of diffusion decoding: emph{regions with strong causal ordering require sequential updates, whereas semantically cohesive regions admit parallel refinement.} We introduce GeoBlock, a […]

Ver mais