arXiv:2605.16046v1 Announce Type: cross Abstract: Semantic code search has been widely adopted in both academia and industry. These approaches embed natural-language queries and code snippets into a shared embedding space and retrieve results based on vector similarity. Despit strong performance on benchmark datasets, they often suffer from poor explainability and generalization. Retrieved code may appear […]
On the Fragility of Data Attribution When Learning Is Distributed
arXiv:2605.15520v1 Announce Type: cross Abstract: Data attribution has become an important component of pricing, auditing, and governance in machine learning pipelines, yet most attribution methods implicitly assume that attribution values faithfully reflect participants’ contributions. We show that this assumption can fail: a single participant in a standard distributed training workflow can substantially inflate its measured […]
Looped SSMs: Depth-Recurrence and Input Reshaping for Time Series Classification
arXiv:2605.16048v1 Announce Type: cross Abstract: State Space Models (SSMs) are inherently recurrent along the sequence dimension, yet depth-recurrence – reusing the same block repeatedly across layers, as recently applied in looped transformers – has not been explored in this model family. We show that a looped SSM with $k$ parameters iterated $L$ times consistently closely […]
Network-Aware Bilinear Tokenization for Brain Functional Connectivity Representation Learning
arXiv:2605.14048v2 Announce Type: replace Abstract: Masked autoencoders (MAEs) have recently shown promise for self-supervised representation learning of resting-state brain functional connectivity (FC). However, a fundamental question remains unresolved: how should FC matrices be tokenized to align with the intrinsic modular organization of large-scale brain networks? Existing approaches typically adopt region-centric or graph-based schemes that treat […]
TFGN: Task-Free, Replay-Free Continual Pre-Training Without Catastrophic Forgetting at LLM Scale
arXiv:2605.15053v2 Announce Type: replace-cross Abstract: Continually pre-training a large language model on heterogeneous text domains, without replay or task labels, has remained an unsolved architectural problem at LLM scale. Existing methods rely on replay buffers, task identifiers, regularization penalties that scale poorly, or sentence-classification-scale evaluation. We introduce TFGN, an architectural overlay for transformer language models […]
Tuning-free Instruction-based Video Editing Via Structural Noise Initialization and Guidance
arXiv:2605.15533v1 Announce Type: cross Abstract: Video editing poses a significant challenge. While a series of tuning-free methods circumvent the need for extensive data collection and model training, they often underutilize the rich information embedded within noisy latent, leading to unsatisfactory results. To address this, we propose a textittuning-free, instruction-based video editing framework. We approach video […]
Conditions for spatial instabilities and pattern formation from monomial steady state parameterizations
arXiv:2605.16049v1 Announce Type: cross Abstract: We study the onset of spatial instabilities in reaction networks where the spatially homogeneous system admits a steady state parameterization. We formulate a sufficient condition — based on the signs of the constant and leading coefficients of the characteristic polynomial of the linearized Jacobian scaled by the diffusion coefficients — […]
A geometry-dependent, force balance-driven model of Staphylococcus epidermidis biofilm cell cluster detachment
arXiv:2605.15364v1 Announce Type: new Abstract: Biofilms, bacteria cells surrounded by a self-produced polymeric matrix, are common on medical devices and lead to many hospital infections. The biofilm lifecycle includes disassembly and dispersion, where bacteria clusters detach from the biofilm, circulate in the bloodstream, and potentially colonize secondary infection sites. Existing models often simplify detachment to […]
ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
arXiv:2605.14309v2 Announce Type: replace-cross Abstract: Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove target knowledge without affecting unrelated semantics. This issue is especially pronounced since a single image often contains multiple entangled concepts, including both target concepts to be forgotten and contextual […]
TokenButler: Token Importance is Predictable
arXiv:2503.07518v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) rely on the Key-Value (KV) Cache to store token history, enabling efficient decoding of tokens. As the KV-Cache grows, it becomes a major memory and computation bottleneck. However, there is an opportunity to alleviate this bottleneck, prior research has shown that only a small subset of […]
Don’t Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
arXiv:2604.14572v3 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) grounds LLM responses in external evidence but treats the model as a passive consumer of search results, with no view of how the corpus is organized or what it has not yet seen. We present Corpus2Skill, which distills a document corpus offline into a hierarchical skill directory […]
Amortized Energy-Based Bayesian Inference
arXiv:2605.15407v1 Announce Type: cross Abstract: We consider amortized Bayesian inference for nonlinear inverse problems in settings where only samples from the joint distribution of parameters and observations are available. Classical methods such as Markov chain Monte Carlo require solving a new inference problem for each observation, which can be computationally prohibitive when inference must be […]