arXiv:2506.05647v4 Announce Type: replace Abstract: We study gradient-based data attribution, aiming to identify which training examples most influence a given output. Existing methods for this task either treat network parameters uniformly or rely on implicit weighting derived from Hessian approximations,…
arXiv:2602.17685v1 Announce Type: new Abstract: This paper addresses the challenge of multi target active debris removal (ADR) in Low Earth Orbit (LEO) by introducing a unified coelliptic maneuver framework that combines Hohmann transfers, safety ellipse proximity operations, and explicit refueling…
arXiv:2602.18148v1 Announce Type: cross Abstract: Inverse design, particularly geometric shape optimization, provides a systematic approach for developing high-performance nanophotonic devices. While numerous optimization algorithms exist, previous global approaches exhibit slow convergence and conversely local search strategies frequently become trapped in…
arXiv:2602.17683v1 Announce Type: new Abstract: Accurate short-term forecasting of vegetation dynamics is a key enabler for data-driven decision support in precision agriculture. Normalized Difference Vegetation Index (NDVI) forecasting from satellite observations, however, remains challenging due to sparse and irregular sampling…
arXiv:2602.17684v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scalability is fundamentally constrained by the availability and reliability of high-quality…
arXiv:2602.17682v1 Announce Type: new Abstract: Consistency-based generative models like Shortcut and MeanFlow achieve impressive results via a target-aware design for solving the Probability Flow ODE (PF-ODE). Typically, such methods introduce a target time $r$ alongside the current time $t$ to…
arXiv:2602.17681v1 Announce Type: new Abstract: Post-training quantization (PTQ) is a widely used approach for reducing the memory and compute costs of large language models (LLMs). Recent studies have shown that applying invertible transformations to activations can significantly improve quantization robustness…
arXiv:2602.17680v1 Announce Type: new Abstract: Existing Protein Language Models (PLMs) often suffer from limited adaptability to multiple tasks and exhibit poor generalization across diverse biological contexts. In contrast, general-purpose Large Language Models (LLMs) lack the capability to interpret protein sequences…
arXiv:2602.14498v2 Announce Type: replace-cross Abstract: We introduce a novel uncertainty-aware multimodal segmentation framework that leverages both radiological images and associated clinical text for precise medical diagnosis. We propose a Modality Decoding Attention Block (MoDAB) with a lightweight State Space Mixer…
arXiv:2602.17686v1 Announce Type: new Abstract: Distilling Chain-of-Thought (CoT) reasoning from large language models into compact student models presents a fundamental challenge: teacher rationales are often too verbose for smaller models to faithfully reproduce. Existing approaches either compress reasoning into single-step,…
