Similar to social media bots that shape public opinion, healthcare and financial decisions, LLM-based ChatBots like ChatGPT can persuade users to alter their behavior. Unlike prior work that persuades via overt-partisan bias or misinformation, we test whether framing alone suffices. We conducted a crowdsourced study, where 336 participants interacted with a neutral or one of two value-framed ChatBots while deciding to alter US defense spending. In this single policy domain with controlled content, participants exposed to value-framed ChatBots significantly changed their budget choices relative to the neutral control. When the frame misaligned with their values, some participants reinforced their original preference, revealing a potentially replicable backfire effect, originally considered rare in the literature. These findings suggest that value-framing alone lowers the barrier for manipulative uses of LLMs, revealing risks distinct from overt bias or misinformation, and clarifying risks to countering misinformation.

The remarkable performance of Large Language Models (LLMs) highly relies on crafted prompts. However, manual prompt engineering is a laborious process, creating a core bottleneck for practical application of LLMs. This phenomenon has led to the emergence of a new research area known as Automatic Prompt Optimization (APO), which develops rapidly in recent years. Existing APO methods such as those based on evolutionary algorithms or trial-and-error approaches realize an efficient and accurate prompt optimization to some extent. However, those researches focus on a single model or algorithm for the generation strategy and optimization process, which limits their performance when handling complex tasks. To address this, we propose a novel framework called Ensemble Learning based Prompt Optimization (ELPO) to achieve more accurate and robust results. Motivated by the idea of ensemble learning, ELPO conducts voting mechanism and introduces shared generation strategies along with different search methods for searching superior prompts. Moreover, ELPO creatively presents more efficient algorithms for the prompt generation and search process. Experimental results demonstrate that ELPO outperforms state-of-the-art prompt optimization methods across different tasks, e.g., improving F1 score by 7.6 on ArSarcasm dataset.

We introduce SkyRL-Agent, a framework for efficient, multi-turn, long-horizon agent training and evaluation. It provides efficient asynchronous dispatching, lightweight tool integration, and flexible backend interoperability, enabling seamless use with existing RL frameworks such as SkyRL-train, VeRL, and Tinker. Using SkyRL-Agent, we train SA-SWE-32B, a software engineering agent trained from Qwen3-32B (24.4% Pass@1) purely with reinforcement learning. We introduce two key components: an optimized asynchronous pipeline dispatcher that achieves a 1.55x speedup over naive asynchronous batching, and a tool-enhanced training recipe leveraging an AST-based search tool to facilitate code navigation, boost rollout Pass@K, and improve training efficiency. Together, these optimizations enable SA-SWE-32B to reach 39.4% Pass@1 on SWE-Bench Verified with more than 2x cost reduction compared to prior models reaching similar performance. Despite being trained solely on SWE tasks, SA-SWE-32B generalizes effectively to other agentic tasks, including Terminal-Bench, BrowseComp-Plus, and WebArena. We further demonstrate SkyRL-Agent's extensibility through case studies on deep research, computer use, and memory agents, each trained using a different training backend.

Trajectory generation has recently drawn growing interest in privacy-preserving urban mobility studies and location-based service applications. Although many studies have used deep learning or generative AI methods to model trajectories and have achieved promising results, the robustness and interpretability of such models are largely unexplored. This limits the application of trajectory generation algorithms on noisy real-world data and their trustworthiness in downstream tasks. To address this issue, we exploit the regular structure in urban trajectories and propose a deep generative model based on the pathlet representation, which encode trajectories with binary vectors associated with a learned dictionary of trajectory segments. Specifically, we introduce a probabilistic graphical model to describe the trajectory generation process, which includes a Variational Autoencoder (VAE) component and a linear decoder component. During training, the model can simultaneously learn the latent embedding of pathlet representations and the pathlet dictionary that captures mobility patterns in the trajectory dataset. The conditional version of our model can also be used to generate customized trajectories based on temporal and spatial constraints. Our model can effectively learn data distribution even using noisy data, achieving relative improvements of $35.4\%$ and $26.3\%$ over strong baselines on two real-world trajectory datasets. Moreover, the generated trajectories can be conveniently utilized for multiple downstream tasks, including trajectory prediction and data denoising. Lastly, the framework design offers a significant efficiency advantage, saving $64.8\%$ of the time and $56.5\%$ of GPU memory compared to previous approaches.

Mobile robotic manipulators (MRMs), which integrate mobility and manipulation capabilities, present significant control challenges due to their nonlinear dynamics, underactuation, and coupling between the base and manipulator subsystems. This paper proposes a novel homogeneous Proportional-Integral-Derivative (hPID) control strategy tailored for MRMs to achieve robust and coordinated motion control. Unlike classical PID controllers, the hPID controller leverages the mathematical framework of homogeneous control theory to systematically enhance the stability and convergence properties of the closed-loop system, even in the presence of dynamic uncertainties and external disturbances involved into a system in a homogeneous way. A homogeneous PID structure is designed, ensuring improved convergence of tracking errors through a graded homogeneity approach that generalizes traditional PID gains to nonlinear, state-dependent functions. Stability analysis is conducted using Lyapunov-based methods, demonstrating that the hPID controller guarantees global asymptotic stability and finite-time convergence under mild assumptions. Experimental results on a representative MRM model validate the effectiveness of the hPID controller in achieving high-precision trajectory tracking for both the mobile base and manipulator arm, outperforming conventional linear PID controllers in terms of response time, steady-state error, and robustness to model uncertainties. This research contributes a scalable and analytically grounded control framework for enhancing the autonomy and reliability of next-generation mobile manipulation systems in structured and unstructured environments.

Palpation, the use of touch in medical examination, is almost exclusively performed by humans. We investigate a proof of concept for an artificial palpation method based on self-supervised learning. Our key idea is that an encoder-decoder framework can learn a $\textit{representation}$ from a sequence of tactile measurements that contains all the relevant information about the palpated object. We conjecture that such a representation can be used for downstream tasks such as tactile imaging and change detection. With enough training data, it should capture intricate patterns in the tactile measurements that go beyond a simple map of forces -- the current state of the art. To validate our approach, we both develop a simulation environment and collect a real-world dataset of soft objects and corresponding ground truth images obtained by magnetic resonance imaging (MRI). We collect palpation sequences using a robot equipped with a tactile sensor, and train a model that predicts sensory readings at different positions on the object. We investigate the representation learned in this process, and demonstrate its use in imaging and change detection.

Training a family of large language models targeting multiple scales and deployment objectives is prohibitively expensive, requiring separate training runs for each different size. Recent work on model compression through pruning and knowledge distillation has reduced this cost; however, this process still incurs hundreds of billions of tokens worth of training cost per compressed model. In this paper, we present Nemotron Elastic, a framework for building reasoning-oriented LLMs, including hybrid Mamba-Attention architectures, that embed multiple nested submodels within a single parent model, each optimized for different deployment configurations and budgets. Each of these submodels shares weights with the parent model and can be extracted zero-shot during deployment without additional training or fine-tuning. We enable this functionality through an end-to-end trained router, tightly coupled to a two-stage training curriculum designed specifically for reasoning models. We additionally introduce group-aware SSM elastification that preserves Mamba's structural constraints, heterogeneous MLP elastification, normalized MSE-based layer importance for improved depth selection, and knowledge distillation enabling simultaneous multi-budget optimization. We apply Nemotron Elastic to the Nemotron Nano V2 12B model, simultaneously producing a 9B and a 6B model using only 110B training tokens; this results in over 360x cost reduction compared to training model families from scratch, and around 7x compared to SoTA compression techniques. Each of the nested models performs on par or better than the SoTA in accuracy. Moreover, unlike other compression methods, the nested capability of our approach allows having a many-in-one reasoning model that has constant deployment memory against the number of models in the family.

The question whether algorithmic trading systems (ATS) can improve human trading in terms of effectiveness is eliciting an increasingly relevant debate among traders and investors, as well as quantitative studies that address this issue through numerical testing [[9]]. In recent years, the discussion regarding whether algorithmic trading systems (ATS) can surpass human traders in terms of efficiency, consistency, and adaptability has gained significant traction in both academic and professional circles. Empirical evidence indicates that algorithmic strategies tend to exhibit superior performance in volatile or declining markets, whereas human-managed funds may retain a relative advantage during upward market trends due to behavioral and intuitive factors [[2]]. Moreover, large-scale behavioral studies reveal that algorithms largely eliminate well-known cognitive biases such as the disposition effect that continue to affect human traders [[23]]. Complementary research has also emphasized the growing integration of artificial intelligence and machine learning methods in modern ATS, which enhances predictive accuracy and execution speed [[7]]. Nonetheless, experimental findings suggest that algorithmic trading may still be constrained by design limitations, challenging the notion of its absolute superiority over human decision-making [[16]]. These findings collectively indicate that algorithmic and human trading approaches might be best viewed as complementary, each offering unique strengths under different market conditions.

Cambrian-S aims to take the first steps towards improving video world models with spatial supersensing by introducing (i) two benchmarks, VSI-Super-Recall (VSR) and VSI-Super-Counting (VSC), and (ii) bespoke predictive sensing inference strategies tailored to each benchmark. In this work, we conduct a critical analysis of Cambrian-S across both these fronts. First, we introduce a simple baseline, NoSense, which discards almost all temporal structure and uses only a bag-of-words SigLIP model, yet near-perfectly solves VSR, achieving 95% accuracy even on 4-hour videos. This shows benchmarks like VSR can be nearly solved without spatial cognition, world modeling or spatial supersensing. Second, we hypothesize that the tailored inference methods proposed by Cambrian-S likely exploit shortcut heuristics in the benchmark. We illustrate this with a simple sanity check on the VSC benchmark, called VSC-Repeat: We concatenate each video with itself 1-5 times, which does not change the number of unique objects. However, this simple perturbation entirely collapses the mean relative accuracy of Cambrian-S from 42% to 0%. A system that performs spatial supersensing and integrates information across experiences should recognize views of the same scene and keep object-count predictions unchanged; instead, Cambrian-S inference algorithm relies largely on a shortcut in the VSC benchmark that rooms are never revisited. Taken together, our findings suggest that (i) current VSI-Super benchmarks do not yet reliably measure spatial supersensing, and (ii) predictive-sensing inference recipes used by Cambrian-S improve performance by inadvertently exploiting shortcuts rather than from robust spatial supersensing. We include the response from the Cambrian-S authors (in Appendix A) to provide a balanced perspective alongside our claims. We release our code at: https://github.com/bethgelab/supersanity

Abstract--Recent advancements in neural audio codecs have not only enabled superior audio compression but also enhanced speech synthesis techniques. Researchers are now exploring their potential as universal acoustic feature extractors for a broader range of speech processing tasks. Building on this trend, we introduce Codec2V ec, the first speech representation learning framework that relies exclusively on discrete audio codec units. This approach offers several advantages, including improved data storage and transmission efficiency, faster training, and enhanced data privacy. We explore masked prediction with various training target derivation strategies to thoroughly understand the effectiveness of this framework. Evaluated on the SUPERB benchmark, Codec2V ec achieves competitive performance compared to continuous-input models while reducing storage requirements by up to 16.5 and training time by 2.3, showcasing its scalability and efficiency. Over the past several years, the speech processing community has rapidly adopted self-supervised learning (SSL) followed by supervised fine-tuning as a general-purpose modeling approach for tasks ranging from automatic speech recognition and emotion recognition to speaker verification [1]- [3].