Variance-based methods recover a Gaussian linear structural equation model (SEM) with equal or suitably constrained error variances, either by recursively identifying the source nodes with smallest conditional variance (top-down method) or sink nodes with highest conditional variance (bottom-up method). We show that th...
Hallucination detection is critical for ensuring the reliability of Large Language Models (LLMs) in real-world deployments. While recent works, such as Semantic Entropy (SE) and Kernel Language Entropy (KLE), identify hallucinations by measuring semantic disagreement across multiple generated responses using Natural La...
Dilrangi Sankalpana, Pragatheeswaran Vipulanandan, Uthayasanker Thayasivam et al.· 0 citations
ScanRefer Multiple queries require spatial disambiguation: several instances of the target class are present, and the referencer must pick one. When per-query logits were never logged, a common substitute is cross-epoch agreement. On the full ScanRefer validation set (9,508 queries; GeoClassifier with ground-truth prop...
Micha{\l} Zakrzewski, Mariia Shpir, Taras Rumezhak et al.· 0 citations
Implicit neural representations (INRs) offer a powerful framework for modeling high-dimensional physical fields, but their training remains inefficient because evaluating dense coordinate grids is computationally expensive. Existing coordinate-pruning strategies rely on local error functions that can oversample correla...
Guang Zhao, Xihaier Luo, Sean McCue et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Studying model training requires checkpoint trajectories, whose storage cost limits temporal resolution. Although adjacent checkpoints are numerically close, existing lossless codecs either operate on XOR bit patterns or ignore trajectory-specific conditional structure. We show that a reference weight's exponent predic...
Aniket Srinivasan Ashok (University of Waterloo)· 0 citations
Facade articulation at building scale is usually resolved manually or through parametric systems that encode design intent as explicit rules. This paper investigates a complementary workflow in which a designer-authored prototype supplies transferable articulation logic. Prototype and target massing are represented as...
High-dimensional sparse recipe formulation in process industries involves nonlinear association of various covariates, bounded by sparsity constraints and multi-criteria tolerances. Traditional physics-based classical methods (such as Kubelka-Munk) fail to generate sparse candidate recipes properly due to their simplif...
M. Fuad, Md. Istiak Adnan, Ridwan Al Aziz· 0 citations
Physics time-series data are central to fundamental discoveries involving dark matter, neutrinos, and gravitational waves. Machine learning has shown strong potential to recover weak scientific signals buried in complex noise. Recent LLM-agent systems further automate ML development, but existing approaches are often d...
Yue Ma, Lucas Venetoulias, Akbota Assan et al.· 0 citations
Predicting which scientific connections will form next can point researchers toward the most promising leads. One successful approach learns representations by sampling paths through publication networks, represented by a hypergraph, that connect scientific entities, concepts, and researchers, approximating how knowled...
Si-Ting Wu, Ryan C. Barron, Phoebe Upton Sanderbeck et al.· 0 citations
Most existing sports datasets are individual-centric or ball-centric, focusing on individual player actions while ignoring interactions among teammates. In badminton doubles, tactical success is governed by rapid team formation and coordination, yet standard resources for modeling these player interactions are scarce....
Guan-Yi Jhang, Chiencheng Chiang, Wei-Kai Chen et al.· 0 citations
Many systems read the latent space of a variational autoencoder (VAE) as discrete codes, and rely on each latent being read back as the code it was written as. Shannon (1948) took such a shared codebook as given; inside a VAE nothing enforces it. We prove that no item of a standard training report can reveal whether th...
Modern experiments increasingly produce rich post-treatment objects---such as text, images, and video---that may provide early surrogate signals for outcomes that are delayed, expensive, or observed only for a subset of participants. A pretrained encoder can turn such an object into a strong generic embedding, but the...
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
