arXiv:2604.16883v1 Announce Type: new Abstract: In long-context decoding for LLMs and LMMs, attention becomes increasingly memory-bound because each decoding step must load a large amount of KV-cache data from GPU memory. Existing acceleration strategies often trade efficiency for accuracy by relying on heuristic pruning that may discard useful information. At a deeper level, they also tend to indiscriminately preserve all high-scoring tokens, treat early tokens as indispensable anchors, or rely on heuristic head routing, reflecting an insufficient mechanistic […]

Ver mais

arXiv:2603.10049v1 Announce Type: new Abstract: Ensemble learning is a well established body of methods for machine learning to enhance predictive performance by combining multiple algorithms/models. Combinatorial Fusion Analysis (CFA) has provided method and practice for combining multiple scoring systems, using rank-score characteristic (RSC) function and cognitive diversity (CD), including ensemble method and model fusion. However, there is no general-purpose Python tool available that incorporate these techniques. In this paper we introduce texttt{InFusionLayer}, a machine learning architecture inspired by […]

Ver mais

Alzheimer’s disease (AD), defined as an abnormal buildup of amyloid plaques and tau tangles in the brain can be diagnosed with high accuracy based on protein biomarkers via PET or CSF analysis. However, due to the invasive nature of biomarker collection, most AD diagnoses are made in memory clinics using cognitive tests and evaluation of hippocampal atrophy based on MRI. While clinical assessment and hippocampal volume show high diagnostic accuracy for amnestic or typical AD (tAD), a substantial […]

Ver mais

For many years, the technology community has believed in the principle of “unbundling”—encouraging founders to build micro-SaaS tools that solve a single, very specific problem exceptionally well. The promises were appealing: more flexibility, deeper specialization, and higher productivity. But by 2026, it seems we have reached a breaking point. We are no longer living in the age of productivity; we are living in the age of “digital fragmentation.” The user has shifted from being a producer to becoming […]

Ver mais

Most pseudo-label selection strategies in semi-supervised learning rely on fixed confidence thresholds, implicitly assuming that prediction confidence reliably indicates correctness. In practice, deep networks are often overconfident: high-confidence predictions can still be wrong, while informative low-confidence samples near decision boundaries are discarded. This paper introduces a Confidence-Variance (CoVar) theory framework that provides a principled joint reliability criterion for pseudo-label selection. Starting from the entropy minimization principle, we derive a reliability measure that combines maximum confidence (MC) with residual-class […]

Ver mais

arXiv:2601.20917v1 Announce Type: new Abstract: We present masked Lagrange reconstruction, a technique that enables threshold ML-DSA (FIPS 204) with arbitrary thresholds $T$ while producing standard 3.3 KB signatures verifiable by unmodified FIPS 204 implementations. Concurrent approaches have limitations: Bienstock et al. (ePrint 2025/1163) achieve arbitrary $T$ but require honest-majority and 37–136 rounds; Celi et al. (ePrint 2026/013) achieve dishonest-majority but are limited to $T leq 6$. Our technique addresses the barrier that Lagrange coefficients grow as $Theta(q)$ for […]

Ver mais

arXiv:2602.22362v1 Announce Type: new Abstract: With the advent of generative AI and large language models, embodied conversational agents are becoming synonymous with online interactions. These agents possess vast amounts of knowledge but suffer from exhibiting limited emotional expressiveness. Without adequate expressions, agents might fail to adapt to users’ emotions, which may result in a sub-optimal user experience and engagement. Most current systems prioritize content based responses, neglecting the emotional context of conversations. Research in this space is currently […]

Ver mais

arXiv:2604.13100v1 Announce Type: new Abstract: The shift toward intent-driven software engineering (often termed “Vibe Coding”) exposes a critical Context-Fidelity Trade-off: vague user intents overwhelm linear reasoning chains, leading to architectural collapse in complex repo-level generation. We propose Contract-Coding, a structured symbolic paradigm that bridges unstructured intent and executable code via Autonomous Symbolic Grounding. By projecting ambiguous intents into a formal Language Contract, our framework serves as a Single Source of Truth (SSOT) that enforces topological independence, effectively isolating […]

Ver mais