We study regression-based data fusion under uncertainty, where multiple noisy and biased measurement sources are available but ground-truth labels are absent during training. This setting arises in sensor networks, simulation ensembles, and scientific monitoring systems where supervision is costly or infeasible. We pro...
Muhammed Faruk Aytin, Zehra Demir, Alper Unal et al.· 0 citations
Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform credit across all tokens, wasting gradient on routine tokens while under-crediting pivotal reasoning steps. Existing token-level credit assig...
Yingyu Shan, Yuhang Guo, Zihao Cheng et al.· 0 citations
Structured State Space Models (SSMs), including the S4 and S4D architectures, have recently emerged as powerful alternatives to attention-based models for capturing long-range dependencies in sequential data. Despite their strong empirical performance, deploying these models in time- and resource-constrained settings r...
Marco Deano, Filippo Ziche, Nicola Bombieri· 0 citations
Current Vision-Language-Action (VLA) models face a trade-off between efficient action generation and explicit deliberation. Directly decoding actions from vision-language backbone representations enables low-latency control, whereas textual reasoning, pixel-level subgoals, or world-model evaluation of decoded actions c...
Bochen Yang, Lianlei Shan· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Vision-language-action (VLA) models increasingly rely on high-frequency multi-camera observations, making visual communication a major bottleneck for real-time robotic control in bandwidth-constrained or distributed deployment settings. Existing image and video codecs, however, are designed to preserve generic visual f...
Hyeonjun Kim, Jegwang Ryu, Sangbeom Ha et al.· 0 citations
Preference optimization is increasingly used to post-train medical large vision-language models (LVLMs), yet it operates at a much coarser granularity than the one that defines clinical correctness. Whether one response is clinically better than another usually comes down to a few decisive phrases, such as an anatomica...
Shayan Mohammadizadehsamakosh, Pritam Sarkar, Leonid Sigal et al.· 0 citations
Modern pretrained self-supervised automatic speech recognition models are trained on large-scale audio data to encode speech into contextualized representations. However, their training data are heavily skewed toward high-resource languages with little data from low-resource languages, raising concerns about the potent...
Chihiro Taguchi, \'Eric Le Ferrand, Hirosi Nakagawa et al.· 0 citations
Language model safety must continually adapt to evolving attacks. Recent works have demonstrated that reinforcement learning can be used to train stronger attacker and defender models in tandem by applying PPO-style self-play and DPO-style online preference optimization. In this work, we explore the efficacy of GRPO in...
Blake Bullwinkel, Eugenia Kim, Amanda Minnich et al.· 0 citations
Implicit chain-of-thought (iCoT) methods aim to internalize reasoning in large language models, but often underperform explicit CoT prompting. We empirically find that hidden-state reasoning trajectories exhibit low-rank structure. Motivated by this observation, we propose a low-rank distillation framework that transfe...
Generative emulators of protein dynamics produce plausible trajectories at a fraction of the cost of molecular dynamics, but they inherit their training distribution and tend to revisit known states rather than reach rare ones under long-horizon extrapolation. Inspired by classical enhanced sampling, we introduce an im...
Kaihui Cheng, Zhiqiang Cai, Wenkai Xiang et al.· 0 citations
Memory is essential for enabling large language models to support long-horizon reasoning, yet existing memory systems remain unreliable and difficult to debug. Tracing memory's dynamic evolution is crucial to understand how information is synthesized, propagated, or corrupted over time. In this work, we study the new p...
Xinle Deng, Ruobin Zhong, Hujin Peng et al.· 0 citations
Large language models (LLMs) for code completion and generation are increasingly used in software development, yet they may reproduce training examples verbatim and without authorship attribution, raising legal and ethical concerns around plagiarism and license compliance. Classical fingerprint-based plagiarism detecto...
Andrea Gurioli, Davide D'Ascenzo, Federico Pennino et al.· 0 citations
