Local curvature of potential energy surfaces is critical for predicting certain experimental observables of molecules and materials from first principles, yet it remains far beyond reach for complex systems. In this work, we introduce a Hessian-informed Machine Learning Interatomic Potential (Hi-MLIP) that captures such curvature reliably, thereby enabling accurate analysis of associated thermodynamic and kinetic phenomena. To make Hessian supervision practically viable, we develop a highly efficient training protocol, termed Hessian INformed Training (HINT), achieving two to four […]

Ver mais

We explore the Traveling Salesman Problem (TSP) using a Variational Quantum Algorithm (VQA), with a focus on representation efficiency and model structure learning rather than just parameter tuning. Key ideas: Compact permutation-based encoding Uses O(nlog⁡n)O(n log n)O(nlogn) qubits and guarantees that every quantum state corresponds to a valid tour (no constraint penalties or repair steps). Adaptive circuit optimization Instead of fixing the quantum circuit (ansatz) upfront, we optimize its structure using Simulated Annealing: add / remove rotation and […]

Ver mais

Hi, I am a PhD student and trying to run a ML reading group focused on interpretability and robustness every weekend. Its always nice to hear different takes and opinions on a paper and this discussion group could serve the purpose. If you are a fellow PhD student or a ML researcher interested in reading recent papers in depth then please fill this google form to be added in the group for receiving further updates on when we […]

Ver mais

Happy New Year, world! As a New Year gift, HackerNoon brings you the grandest developer hackathon of 2026. The internet is overflowing with software that looks impressive, sounds intelligent, and quietly fails to help anyone. We’ve normalized pitch decks for products that don’t exist, AI demos with no users, and MVPs that launch with applause and vanish without a trace. Meanwhile, people still need tools that work. So we’re doing something different. Enters the Proof of Usefulness Hackathon! From […]

Ver mais

arXiv:2604.05039v1 Announce Type: new Abstract: Humans have remarkable selective sensitivity to identities — easily distinguishing between highly similar identities, even across significantly different contexts such as diverse viewpoints or lighting. Vision models have struggled to match this capability, and progress toward identity-focused tasks such as personalized image generation is slowed by a lack of identity-focused evaluation metrics. To help facilitate progress, we propose ID-Sim, a feed-forward metric designed to faithfully reflect human selective sensitivity. To build ID-Sim, we […]

Ver mais

arXiv:2601.16381v1 Announce Type: new Abstract: Few-Shot Anomaly Detection (FSAD) has emerged as a critical paradigm for identifying irregularities using scarce normal references. While recent methods have integrated textual semantics to complement visual data, they predominantly rely on features pre-trained on natural scenes, thereby neglecting the granular, domain-specific semantics essential for industrial inspection. Furthermore, prevalent fusion strategies often resort to superficial concatenation, failing to address the inherent semantic misalignment between visual and textual modalities, which compromises robustness against cross-modal […]

Ver mais

arXiv:2406.07746v3 Announce Type: replace Abstract: We propose a computationally efficient algorithm that achieves anytime regret of order $mathcal{O}(sqrt{t})$, with explicit dependence on the system dimensions and on the solution of the Discrete Algebraic Riccati Equation (DARE). Our approach builds on the SDP-based framework of cite{cohen2019learning}, using an appropriately tuned regularization and a sufficiently accurate initial estimate to construct confidence ellipsoids for control design. A carefully designed input-perturbation mechanism is incorporated to ensure anytime performance. We develop two variants […]

Ver mais