arXiv preprints from January 1, 2026 through July 28, 2026 — 08:04:39 EST
Aligning language models to qualitative behavioral traits, such as human-likeness, remains difficult because they are hard to define, measure, and optimize. As a result, improvements in human-like behavior are largely driven by scale or broad supervised training, rather than targeted alignment. We introduce Human Aligning LLMs (HAL),...
Diverse and enriched data sources are essential for commercial ads-recommendation models to accurately assess user interest both before and after engagement with content. While extended user-engagement histories can improve the prediction of user interests, it is equally important to embed activity sequences from multiple sources to...
Immunohistochemical (IHC) staining provides crucial molecular characterization of tissue samples and plays an indispensable role in the clinical examination and diagnosis of cancers. However, compared with the commonly used Hematoxylin and Eosin (H&E) staining, IHC staining involves complex procedures and is both time-consuming and...
Alignment in large language models (LLMs) is still largely static: after training, the policy is frozen. DPO, GRPO methods typically imprint one behavior into the weights, leaving little runtime control beyond prompt hacks or expensive re-alignment. We introduce ECLIPTICA, which treats alignment as instruction-driven and...
Video see-through (VST) technology aims to seamlessly blend virtual and physical worlds by reconstructing reality through cameras. While manufacturers promise perceptual fidelity, it remains unclear how close these systems are to replicating natural human vision across varying environmental conditions. In this work, we quantify the...
Rewriting Induction (RI) is a method to prove inductive theorems, originating from equational reasoning. By using Logically Constrained Simply-typed Term Rewriting Systems (LCSTRSs) as an intermediate language, rewriting induction becomes a tool for program verification, with inductive theorems taking the role of equivalence...
The efficient construction of accurate channel knowledge maps (CKMs) is crucial for unleashing the full potential of environment-aware wireless networks, yet it remains a difficult ill-posed problem due to the sparsity of available location-specific channel knowledge data. Although diffusion-based methods such as denoising diffusion...
The task of jointly communicating a message and reconstructing a common estimate of the channel state is examined for a fading Gaussian model with additive state interference. The state is an independent and identically distributed Gaussian sequence known noncausally at the transmitter, and the instantaneous fading coefficient is...
Uniform-noise discrete diffusion and flow models (e.g., D3PM, SEDD, UDLM, DFM) generate sequences non-autoregressively by iteratively refining randomly initialized vocabulary tokens through multiple context-dependent replacements. These models are typically formulated as time-inhomogeneous CTMC/DTMC processes and sampled using...
Autonomous navigation is crucial for both medical and industrial endoscopic robots, enabling safe and efficient exploration of narrow tubular environments without continuous human intervention, where avoiding contact with the inner walls has been a longstanding challenge for prior approaches. We present a follow-the-leader endoscopic...
Rapid motorization in emerging economies such as India has created severe enforcement asymmetries, with over 11 million recorded violations in 2023 against a human policing density of roughly one officer per 4000 vehicles. Traditional surveillance and manual ticketing cannot scale to this magnitude, motivating the need for an...
Applying single image Monocular Depth Estimation (MDE) models to video sequences introduces significant temporal instability and flickering artifacts. We propose a novel approach that adapts any state-of-the-art image-based (depth) estimation model for video processing by integrating a new temporal module - trainable on a single GPU...
We introduce Textile IR, a bidirectional intermediate representation that connects manufacturing-valid CAD, physics-based simulation, and lifecycle assessment for fashion design. Unlike existing siloed tools where pattern software guarantees sewable outputs but understands nothing about drape, and physics simulation predicts behaviour...
Accurate radio map (RM) construction is essential to enabling environment-aware and adaptive wireless communication. However, in future 6G scenarios characterized by high-speed network entities and fast-changing environments, it is very challenging to meet real-time requirements. Although generative diffusion models (DMs) can achieve...
Video stylization, an important downstream task of video generation models, has not yet been thoroughly explored. Its input style conditions typically include text, style image, and stylized first frame. Each condition has a characteristic advantage: text is more flexible, style image provides a more accurate visual anchor, and...
Earth vision has achieved milestones in geospatial object recognition but lacks exploration in object-relational reasoning, limiting comprehensive scene understanding. To address this, a progressive Earth vision-language understanding and generation framework is proposed, including a multi-task dataset (EarthVLSet) and a...
We present MiMo-V2-Flash, a Mixture-of-Experts (MoE) model with 309B total parameters and 15B active parameters, designed for fast, strong reasoning and agentic capabilities. MiMo-V2-Flash adopts a hybrid attention architecture that interleaves Sliding Window Attention (SWA) with global attention, with a 128-token sliding window under...
Human-like dexterous hands with multiple fingers offer human-level manipulation capabilities, but training control policies that can directly deploy on real hardware remains difficult due to contact-rich physics and imperfect actuation. We close this gap with a practical sim-to-real reinforcement learning (RL) framework that utilizes...
Agile locomotion in legged robots poses significant challenges for visual perception. Traditional frame-based cameras often fail in these scenarios for producing blurred images, particularly under low-light conditions. In contrast, event cameras capture changes in brightness asynchronously, offering low latency, high temporal...
Neural Audio Codecs (NACs) can reduce transmission overhead by performing compact compression and reconstruction, which also aim to bridge the gap between continuous and discrete signals. Existing NACs can be divided into two categories: multi-codebook and single-codebook codecs. Multi-codebook codecs face challenges such as...
Organizations use asynchronous AI interview systems to efficiently manage large applicant pools, enabling quick and uniform evaluations. However, concerns remain about their impact on user agency and the lack of personalization applicants experience with these systems. Although efforts have been made to humanize the interview process,...
This essay examines the evolving concept of legal personality through the lens of recent developments in artificial intelligence and the possible emergence of superintelligence. Legal systems have long been open to extending personhood to non-human entities, most prominently corporations, for instrumental or inherent reasons....
Visual abductive reasoning (VAR) is a challenging task that requires AI systems to infer the most likely explanation for incomplete visual observations. While recent MLLMs develop strong general-purpose multimodal reasoning capabilities, they fall short in abductive inference, as compared to human beings. To bridge this gap, we draw...
Assistive electric-powered wheelchairs (EPWs) have become essential mobility aids for people with disabilities such as amyotrophic lateral sclerosis (ALS), post-stroke hemiplegia, and dementia-related mobility impairment. This work presents a novel multi-modal EPW control system designed to prioritize patient needs while allowing...
Large language models (LLMs) have demonstrated success in various applications of user recommendation and personalization across e-commerce and entertainment. On many entertainment platforms such as Netflix, users typically interact with a wide range of titles, each represented by an artwork. Since users have diverse preferences, an...