arXiv:2602.03317v1 Announce Type: new Abstract: Quantitative imaging methods, such as magnetic resonance fingerprinting (MRF), aim to extract interpretable pathology biomarkers by estimating biophysical tissue parameters from signal evolutions. However, the pattern-matching algorithms or neural networks used in such inverse problems often lack principled uncertainty quantification, which limits the trustworthiness and transparency, required for clinical acceptance. Here, we describe a physics-structured variational autoencoder (PS-VAE) designed for rapid extraction of voxelwise multi-parameter posterior distributions. Our approach integrates a differentiable spin […]

Ver mais

A zero knowledge proof (ZKP) answers a question without revealing anything more than answer. For example, a digital signature proves your possession of a private key without revealing that key. Here’s another example, one that’s more concrete than a digital signature. Suppose you have a deck of 52 cards, 13 of each of spades, hearts, diamonds, and clubs. If I draw a spade from the deck, I can prove that I drew a spade without showing which card […]

Ver mais

arXiv:2506.13107v3 Announce Type: replace-cross Abstract: Causal forests estimate how treatment effects vary across individuals, guiding personalized interventions in areas like marketing, operations, and public policy. A standard modeling practice with this method is honest estimation: dividing the data into two samples, one to define subgroups and another to estimate treatment effects within them. This is intended to reduce overfitting and is the default in many software packages. But is it the right choice? In this paper, we show […]

Ver mais

arXiv:2603.00632v1 Announce Type: new Abstract: Semantic IDs (SIDs) are compact discrete representations derived from multimodal item features, serving as a unified abstraction for ID-based and generative recommendation. However, learning high-quality SIDs remains challenging due to two issues. (1) Collision problem: the quantized token space is prone to collisions, in which semantically distinct items are assigned identical or overly similar SID compositions, resulting in semantic entanglement. (2) Collision-signal heterogeneity: collisions are not uniformly harmful. Some reflect genuine conflicts between […]

Ver mais

arXiv:2601.00229v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) method has emerged as a dominant paradigm for adapting pre-trained GNN models to downstream tasks. However, existing PEFT methods usually exhibit significant vulnerability to various noise and attacks on graph topology and node attributes/features. To address this issue, for the first time, we propose integrating adversarial learning into graph prompting and develop a novel Adversarial Graph Prompting (AGP) framework to achieve robust graph fine-tuning. Our AGP has two key aspects. […]

Ver mais

arXiv:2601.09869v1 Announce Type: new Abstract: Anthropomorphisation — the phenomenon whereby non-human entities are ascribed human-like qualities — has become increasingly salient with the rise of large language model (LLM)-based conversational agents (CAs). Unlike earlier chatbots, LLM-based CAs routinely generate interactional and linguistic cues, such as first-person self-reference, epistemic and affective expressions that empirical work shows can increase engagement. On the other hand, anthropomorphisation raises ethical concerns, including deception, overreliance, and exploitative relationship framing, while some authors argue that […]

Ver mais

arXiv:2602.04988v1 Announce Type: new Abstract: We propose a new and simplified multiscale time integrator Fourier pseudospectral (MTI-FP) method for the nonlinear Klein-Gordon equation (NKGE) with a dimensionless parameter epsilon in (0,1] inversely proportional to the speed of light, and establish its uniform first-order accuracy in time in the nonrelativistic regime, i.e. 0 < epsilon << 1. In this regime, the solution of the NKGE is highly oscillatory in time with O(epsilon^2)-wavelength, which brings significant difficulties in designing uniformly […]

Ver mais

Happy to share the latest colqwen3.5-4.5B model in the series. ColQwen3.5-4.5B-v3 is #1 (avg) on the MTEB ViDoRe leaderboard (Pending release) at 75.67 mean, ~half the params, ~13x fewer embedding dims, ~half the memory footprint of the previous #1 model. Thoughts: V3 edges out v2 on V3 English u@5 (0.6034 vs 0.6023), a marginal gain for substantially more compute. The real win was the V2 benchmark jump and surpassing 8B models on V3. That’s where I decided to […]

Ver mais