The impressive performance gains of modern language models currently rely on scaling parameters: larger models store more world knowledge and reason better. Yet compressing all world knowledge into parameters is unnecessary, as only a fraction is used per prompt, and impractical for edge devices with limited inference-time memory and compute. We address this shortcoming by a memory-augmented architecture and a pretraining strategy aligned with existing hardware paradigms. We introduce small language models that access large hierarchical parametric memory banks encoding world knowledge. During pretraining and inference, we fetch a small, context-dependent memory block and add it to the model. Our pretraining learns to store long-tail world knowledge in the memory parameters, while the small language model acts as an anchor capturing common knowledge and general reasoning abilities. Through trillion-token-scale experiments, we show significant gains: a 160M-parameters model augmented with an 18M-parameters memory fetched from a 4.6B memory bank obtains comparable performance to a regular model with more than 2x the parameters. Through extensive experiments, we study the optimal type and size of parametric memories in transformers, scaling them to over 21B parameters. We find that our proposed hierarchical feed-forward memories work robustly across transformer architectures, whether added during pretraining or post-hoc.

In this short paper, we present work evaluating an AI agent's understanding of spoken conversations about data visualizations in an online meeting scenario. There is growing interest in the development of AI-assistants that support meetings, such as by providing assistance with tasks or summarizing a discussion. The quality of this support depends on a model that understands the conversational dialogue. To evaluate this understanding, we introduce a dual-axis testing framework for diagnosing the AI agent's comprehension of spoken conversations about data. Using this framework, we designed a series of tests to evaluate understanding of a novel corpus of 72 spoken conversational dialogues about data visualizations. We examine diverse pipelines and model architectures, LLM vs VLM, and diverse input formats for visualizations (the chart image, its underlying source code, or a hybrid of both) to see how this affects model performance on our tests. Using our evaluation methods, we found that text-only input modalities achieved the best performance (96%) in understanding discussions of visualizations in online meetings.

Recent advances in large language models (LLMs) highlight the importance of training data structure and quality in shaping reasoning behavior. However, most existing approaches focus on transforming data formats while neglecting the internal reasoning complexity of training samples, leaving the reasoning potential of data under-explored and underutilized. In this work, we posit that LLM logical reasoning performance is jointly constrained by the potential of the training data and the cognitive capacity of the model. To make this relationship measurable, we introduce Data Reasoning Intensity (DRI), a novel metric that quantifies the latent logical reasoning complexity of samples by decomposing and aggregating their logical structures. This allows us to analyze how well current LLMs utilize logical reasoning signals and identify performance gaps relative to data potential. Based on this insight, we introduce a re-cognizing optimization strategy that systematically enhances the logical reasoning intensity of training data. Rather than increasing data volume, our method re-optimizes existing samples to better align with the LLM's logical reasoning boundary. Extensive experiments show that our approach significantly improves performance and generalization over data-centric strategies. We further validate our method under a reinforcement learning framework. Our results indicate that prioritizing reasoning complexity in data rather than sheer scale or superficial form is essential to realizing LLMs' full cognitive potential.

We present NanoFlux, a novel adversarial framework for generating targeted training data to improve LLM reasoning, where adversarially-generated datasets of 200 examples outperform conventional fine-tuning approaches. The framework employs a competitive dynamic between models alternating as Attacker and Defender, supervised by a tool-augmented Judge, synthesizing multi-step questions with explanatory annotations that target specific reasoning capabilities. Fine-tuning a 4B-parameter model on NanoFlux-generated data yields performance gains across diverse domains compared to full-benchmark fine-tuning: +5.9% on mathematical reasoning (GSMHard), +3.6% on scientific reasoning (GenomeBench), and +16.6% on medical reasoning (MultiMedQA), while reducing computational requirements by 3-14 . Ablation studies reveal a nonmonotonic relationship between dataset characteristics and model performance, uncovering domain-specific optimal points for question complexity and reasoning quality. NanoFlux automates training data generation through embedding-based novelty filtering, tool-augmented evaluation, and multi-hop reasoning, suggesting that future model improvements may lie in the intelligent synthesis of small, precisely targeted training datasets. As large language models (LLMs) rapidly approach and surpass human-level performance on established benchmarks, we confront a fundamental limitation: the finite nature of high-quality training data. Today's frontier models have effectively consumed the entirety of available text on the internet, yet continue to exhibit critical reasoning failures and knowledge gaps. This "benchmark exhaustion" phenomenon raises crucial questions about how to advance AI capabilities beyond the constraints of existing data. While generating synthetic training examples represents one potential path forward, creating effective synthetic data remains challenging - naive generation approaches often produce low-information samples that fail to improve model performance, while synthesizing effective datasets typically requires precisely the kind of human expertise and curation that we seek to automate. Recent work, notably LIMO (Y e et al., 2025), has demonstrated that small, carefully cu-rated datasets of high-quality chain-of-thought solutions can unlock strong reasoning performance, but still depends on human effort in curation. We introduce NanoFlux, a fully generative adversarial framework that reimagines data-efficient reasoning improvement. NanoFlux orchestrates a competitive dynamic between two models alternating as Attacker and Defender, supervised by a tool-augmented Judge that evaluates responses for accuracy, coherence, and safety (as shown in Figure 1).

Reinforcement learning (RL) and sim-to-real transfer have advanced robotic manipulation of rigid objects. Yet, policies remain brittle when applied to articulated mechanisms due to contact-rich dynamics and under-modeled joint phenomena such as friction, stiction, backlash, and clearances. We address this challenge through dexterous in-hand manipulation of articulated tools using a robotic hand with reduced articulation and kinematic redundancy relative to the human hand. Our controller augments a simulation-trained base policy with a sensor-driven refinement learned from hardware demonstrations, conditioning on proprioception and target articulation states while fusing whole-hand tactile and force feedback with the policy's internal action intent via cross-attention-based integration. This design enables online adaptation to instance-specific articulation properties, stabilizes contact interactions, regulates internal forces, and coordinates coupled-link motion under perturbations. We validate our approach across a diversity of real-world examples, including scissors, pliers, minimally invasive surgical tools, and staplers. We achieve robust transfer from simulation to hardware, improved disturbance resilience, and generalization to previously unseen articulated tools, thereby reducing reliance on precise physical modeling in contact-rich settings.

Abstract--This study introduces a haptic shared control framework designed to teach human drivers advanced driving skills. In this context, shared control refers to a driving mode where the human driver collaborates with an autonomous driving system to control the steering of a vehicle simultaneously. Advanced driving skills are those necessary to safely push the vehicle to its handling limits in high-performance driving such as racing and emergency obstacle avoidance. Previous research has demonstrated the performance and safety benefits of shared control schemes using both subjective and objective evaluations. However, these schemes have not been assessed for their impact on skill acquisition on complex and demanding tasks. Prior research on long-term skill acquisition either applies haptic shared control to simple tasks or employs other feedback methods like visual and auditory aids. T o bridge this gap, this study creates a cyber racing coach framework based on the haptic shared control paradigm and evaluates its performance in helping human drivers acquire high-performance driving skills. The framework introduces (1) an autonomous driving system that is capable of cooperating with humans in a highly performant driving scenario; and (2) a haptic shared control mechanism along with a fading scheme to gradually reduce the steering assistance from autonomy based on the human driver's performance during training. Two benchmarks are considered: self-learning (no assistance) and full assistance during training. Results from a human subject study indicate that the proposed framework helps human drivers develop superior racing skills compared to the benchmarks, resulting in better performance and consistency. Advanced driving skills refer to a set of competencies that go beyond basic driving abilities in terms of situational awareness, hazard perception, risk management, and vehicle handling [1]. They are crucial in high-performance driving tasks such as racing, and can also improve safety in everyday driving [1], [2]. This work has been submitted to the IEEE for possible publication.

The top row shows the starting object configuration with its goal rendered as a transparent overlay, while the bottom row shows the result after the robot's motion. GD2P synthesizes diverse hand poses conditioned on object geometry, handling flat (left), volumetric (middle), and tall (right) objects. Grey arrows represent the transporting direction, whereas white volumetric dots mark the estimated fingertip contact with the object. Abstract-- Nonprehensile manipulation, such as pushing and pulling, enables robots to move, align, or reposition objects that may be difficult to grasp due to their geometry, size, or relationship to the robot or the environment. Much of the existing work in nonprehensile manipulation relies on parallel-jaw grippers or tools such as rods and spatulas. In contrast, multi-fingered dexterous hands offer richer contact modes and versatility for handling diverse objects to provide stable support over the objects, which compensates for the difficulty of modeling the dynamics of nonprehensile manipulation. Therefore, we propose G eometry-aware D exterous P ushing and P ulling (GD2P) for nonprehensile manipulation with dexterous robotic hands. We study pushing and pulling by framing the problem as synthesizing and learning pre-contact dexterous hand poses that lead to effective manipulation. We generate diverse hand poses via contact-guided sampling, filter them using physics simulation, and train a diffusion model conditioned on object geometry to predict viable poses. At test time, we sample hand poses and use standard motion planners to select and execute pushing and pulling actions. GSS holds concurrent appointments as a Professor at USC and as an Amazon Scholar. This paper describes work performed at USC and is not associated with Amazon. All authors are with the Thomas Lord Department of Computer Science at the University of Southern California, USA.

Improving pretraining data quality and size is known to boost downstream performance, but the role of text complexity--how hard a text is to read--remains less explored. We reduce surface-level complexity (shorter sentences, simpler words, simpler structure) while keeping core content approximately constant and ask: (i) How does complexity affect language modeling across model sizes? (ii) Can useful representations be learned from simpler text alone? (iii) How does pretraining text complexity influence downstream language understanding? We simplify human-written texts using a large language model, pretrain causal models (28M-500M) from scratch on original vs. simplified data, and evaluate them in fine-tuning and zero-shot setups. We find that perplexity is sensitive to the interaction between model capacity and text complexity--smaller models degrade far less on simpler texts--while text complexity has little impact on fine-tuning evaluations, with zero-shot evaluations indicating that simpler texts benefit performance on linguistic knowledge tasks, whereas more complex texts favor tasks requiring world knowledge and entity tracking. Our findings suggest that different types of data diversity affect transfer and zero-shot performance differently, providing insight into tailoring data curation to specific goals.

Large language models (LLMs) are increasingly applied in diverse real-world scenarios, each governed by bespoke behavioral and safety specifications (spec) custom-tailored by users or organizations. These spec, categorized into safety-spec and behavioral-spec, vary across scenarios and evolve with changing preferences and requirements. We formalize this challenge as specification alignment, focusing on LLMs' ability to follow dynamic, scenario-specific spec from both behavioral and safety perspectives. To address this challenge, we propose Align3, a lightweight method that employs Test-Time Deliberation (TTD) with hierarchical reflection and revision to reason over the specification boundaries. We further present SpecBench, a unified benchmark for measuring specification alignment, covering 5 scenarios, 103 spec, and 1,500 prompts. Experiments on 15 reasoning and 18 instruct models with several TTD methods, including Self-Refine, TPO, and MoreThink, yield three key findings: (i) test-time deliberation enhances specification alignment; (ii) Align3 advances the safety-helpfulness trade-off frontier with minimal overhead; (iii) SpecBench effectively reveals alignment gaps. These results highlight the potential of test-time deliberation as an effective strategy for reasoning over the real-world specification boundaries.

Recent advances in large language models (LLMs) have enabled human-like social simulations at unprecedented scale and fidelity, offering new opportunities for computational social science. A key challenge, however, is the construction of persona sets that authentically represent the diversity and distribution of real-world populations. Most existing LLM-based social simulation studies focus primarily on designing agentic frameworks and simulation environments, often overlooking the complexities of persona generation and the potential biases introduced by unrepresentative persona sets. In this paper, we propose a systematic framework for synthesizing high-quality, population-aligned persona sets for LLM-driven social simulation. Our approach begins by leveraging LLMs to generate narrative personas from long-term social media data, followed by rigorous quality assessment to filter out low-fidelity profiles. We then apply importance sampling to achieve global alignment with reference psychometric distributions, such as the Big Five personality traits. To address the needs of specific simulation contexts, we further introduce a task-specific module that adapts the globally aligned persona set to targeted subpopulations. Extensive experiments demonstrate that our method significantly reduces population-level bias and enables accurate, flexible social simulation for a wide range of research and policy applications.