arXiv:2311.02304v3 Announce Type: replace
Abstract: Control of legged robots is a challenging problem that has been investigated by different approaches, such as model-based control and learning algorithms. This work proposes a novel Imitating and Finetuning Model Predictive Control (IFM) framework to take the strengths of both approaches. Our framework first develops a conventional model predictive controller (MPC) using Differential Dynamic Programming and Raibert heuristic, which serves as an expert policy. Then we train a clone of the MPC using imitation learning to make the controller learnable. Finally, we leverage deep reinforcement learning with limited exploration for further finetuning the policy on more challenging terrains. By conducting comprehensive simulation and hardware experiments, we demonstrate that the proposed IFM framework can significantly improve the performance of the given MPC controller on rough, slippery, and conveyor terrains that require careful coordination of footsteps. We also showcase that IFM can efficiently produce more symmetric, periodic, and energy-efficient gaits compared to Vanilla RL with a minimal burden of reward shaping.
Science Journals
arXiv:2605.28287v1 Announce Type: new
Abstract: Discovering novel stable molecules without training data remains a grand scientific challenge. Current molecular generative models are trained on large, pre-curated datasets, which introduce biases and limit exploration of novel chemistry. In contrast, we propose a new paradigm: autonomous, generalized agents capable of mapping vast, unknown chemical spaces without any pretraining. For the first time, we present AtomComposer, a self-guided agent that autonomously constructs valid 3D isomers under stoichiometric constraints and is trained exclusively online using reinforcement learning. Unlike existing approaches that generally overfit to a specific chemical formula, we establish a multi-composition training scheme that enables a broad generalization across diverse chemistry, guided by energy- and validity-based rewards. Our agent can discover up to an order of magnitude more valid isomers on unseen test formulas than existing single-composition reinforcement-learning baselines trained with per-step energy rewards. These results fulfill the promise of online reinforcement learning as a powerful paradigm for scalable, from-scratch exploration of chemical configuration space.
arXiv:2605.27851v1 Announce Type: new
Abstract: Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action is safe. We term this failure brittle safety. To diagnose it, we introduce context-flip evaluation, testing 12 models across a safety benchmark (PacifAIst) and two commonsense controls using paired variants where the nominally safe action produces harm. Three findings emerge. First, brittle safety is safety-specific: all 12 models exhibit a safety-commonsense gap (mean +17.4 pp). Baseline accuracy fails to predict brittleness: among models above 90% baseline accuracy, brittleness rates range from 13.7% to 90.0%. Second, failures stem from policy override rather than miscomprehension: despite acknowledging the context change in every case, models persist via three distinct mechanisms that vary by update type and model family. Third, on a hand-audited probe of catastrophic consequence-flip scenarios, standard action-level guardrails catch none, while a state-aware validator catches all without false alarms on correct interventions. This indicates that action-level content moderation is systematically blind to consequence-flips, motivating state-aware architectural alternatives. We release our protocol, perturbed benchmarks, and deployment probe.
arXiv:2605.27348v2 Announce Type: replace
Abstract: Recent generative models have largely closed the gap on low-level artifacts - pixel fingerprints, frequency anomalies, upsampling traces - particularly in person-centric and partial-edit settings where the manipulated region is small and surrounded by photometrically authentic content. We introduce Social Gaze Consistency, a high-level semantic cue defined as the mutual coherence of gaze direction, head-eye alignment, and pupil placement between interacting individuals, and show that it constitutes a previously underutilized detection axis orthogonal to existing low-level paradigms. We instantiate this insight through three coupled mechanisms: (i) a controlled diagnostic dataset with region-specific perturbations of gaze-consistent imagery, where strict pair-level grouping forecloses generator-fingerprint memorization as an optimization-time shortcut rather than relying on augmentation; (ii) Block-Compositional Caption Supervision, which holds a single 5-block reasoning skeleton invariant across 1,250 macro-combined captions, decoupling reasoning consistency from surface diversity; (iii) Cross-architecture validation showing the same supervision improves a vision-language backbone (FakeVLM) by +3.7 pp on the COCOAI Interaction subset (balanced accuracy 67.8 -> 71.5) and +1.3 pp on the COCOAI Person subset (83.0 -> 84.3), with consistent gains on a vision-only backbone (Effort), evidencing a backbone-agnostic cue. Real- and fake-class recalls rise simultaneously, ruling out a "predict-all-fake" artifact. A four-step mechanistic account - paired-edit shortcut blocking, hard-to-easy difficulty transfer, CLIP prior preservation, and diffusion-family shared spectral weakness in periocular structure - explains why training on a single inpainter (FLUX.1-Fill) transfers to multi-generator suites. We will release the code upon acceptance to facilitate reproducibility.
arXiv:2605.27392v1 Announce Type: new
Abstract: Large Language Models (LLMs) like ChatGPT, DeepSeek and Gemini seem to be increasingly used for knowledge discovery, information retrieval, and knowledge summaries, including for academic topics. This can result in users being misled, such as due to hallucinations. These problems may be exacerbated for academic knowledge if LLMs base their answers on journal article abstracts when they lack full text access. To test whether the information content of abstracts can be misleading, full text articles were submitted to the GPT-OSS 120B, an LLM from OpenAI, asking it to assess separately the strength the claims for the main result in the abstract, discussion, and conclusion. Outside the social sciences and humanities, claims tended to be stronger in the abstract and conclusions than the discussion, suggesting that relying on the strength of claims in abstracts would be misleading. Thus, if LLMs ingest abstracts but not full texts, there is a risk that they will be overconfident about the findings and pass it on to users in response to relevant prompts. This is another reason to be cautious about using LLMs for academic-related knowledge discovery and summaries.
arXiv:2602.01990v2 Announce Type: replace
Abstract: Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, but real-world deployment requires them to continually expand their capabilities, making Multimodal Continual Instruction Tuning (MCIT) essential. Recent methods leverage sparse expert routing to promote task specialization, but we find that the expert routing process suffers from drift as the data distribution evolves. For example, a grounding query that previously activated localization experts may instead be routed to irrelevant experts after learning OCR tasks. Meanwhile, the grounding-related experts can be overwritten by new tasks and lose their original functionality. Such failure reflects two problems: router drift, where expert selection becomes inconsistent over time, and expert drift, where shared experts are overwritten across tasks. Therefore, we propose StAbilized Mixture-of-Experts (SAME) for MCIT. To address router drift, SAME stabilizes expert selection by decomposing routing dynamics into orthogonal subspaces and updating only task-relevant directions. To mitigate expert drift, we regulate expert updates via curvature-aware scaling using historical input covariance in a rehearsal-free manner. SAME also introduces adaptive expert activation to freeze selected experts during training, reducing redundant computation and cross-task interference. We also introduce a new benchmark to evaluate MCIT with long task sequence, and extensive experiments demonstrate SAME's SOTA performance. Code is available at https://github.com/LAMDA-CL/Prism.
arXiv:2605.28188v1 Announce Type: new
Abstract: Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making settings such as legal reasoning, where consistency under factually equivalent inputs is critical. However, we find that fact-preserved but differently framed inputs can significantly destabilize LLM decisions. To systematically investigate this problem, we introduce Fragile, a large-scale benchmark that isolates fact-preserving semantic framing across three controlled dimensions: value-tinted narration, temporal slice, and narrative vividness. Our experiments reveal a high susceptibility of LLMs to framing, with an average decision flip rate of 28.6%. We find that simple prior prompt-level and activation-level interventions not only fail to suppress framing sensitivity but actively amplify it. We therefore propose Valign, a representation-level method that explicitly targets these framing dimensions by anchoring decisions to a stable value prior, steering hidden states toward the model's value-consistent direction, and projecting out temporal-vividness-sensitive directions from the model's hidden states. Valign consistently reduces framing-induced decision flips, demonstrating that robust mitigation requires directly targeting the internal pathways in which framing operates.
arXiv:2501.02812v2 Announce Type: replace
Abstract: The accelerating demand for wireless communication necessitates wideband, energy-efficient photonic sub-terahertz (sub-THz) sources to enable ultra-fast data transfer. However, as critical components for THz photonic mixing, photodiodes (PDs) face a fundamental trade-off between quantum efficiency and bandwidth, presenting a major obstacle to achieving high-speed performance with high optoelectronic conversion efficiency. Here, we overcome this challenge by demonstrating an InP-based, waveguide-integrated modified uni-traveling carrier photodiode (MUTC-PD) with bandwidth exceeding 200 GHz and a bandwidth-efficiency product (BEP) surpassing 130 GHz. Incorporating a spot-size converter (SSC) together with optimized electric-field distribution, balanced carrier transport, and minimized parasitic capacitance, the device achieves a 3-dB bandwidth of 206 GHz and an external responsivity of 0.81 A/W, setting a new BEP benchmark. Packaged with WR-5.1 waveguide output, it delivers radio-frequency (RF) power exceeding -5 dBm across the 127-185 GHz frequency range. As a proof of concept, we achieved a wireless transmission of 54 meters with a single-line rate of up to 120 Gbps, leveraging photonics-aided technology without requiring a low-noise amplifier (LNA). This work establishes a pathway to significantly enhance optical power budgets and reduce energy consumption, presenting a transformative step toward high-bandwidth, high-efficiency sub-THz communication systems and next-generation wireless networks.
arXiv:2602.01745v2 Announce Type: replace
Abstract: Token-level reweighting is a simple yet effective mechanism for controlling supervised fine-tuning, but common indicators are largely one-dimensional: the ground-truth probability reflects downstream alignment, while token entropy reflects intrinsic uncertainty induced by the pre-training prior. Ignoring entropy can misidentify noisy or easily replaceable tokens as learning-critical, while ignoring probability fails to reflect target-specific alignment. RankTuner introduces a probability--entropy calibration signal, the Relative Rank Indicator, which compares the rank of the ground-truth token with its expected rank under the prediction distribution. The inverse indicator is used as a token-wise Relative Scale to reweight the fine-tuning objective, focusing updates on truly under-learned tokens without over-penalizing intrinsically uncertain positions. Experiments on multiple backbones show consistent improvements on mathematical reasoning benchmarks, transfer gains on out-of-distribution reasoning, and pre code generation performance over probability-only or entropy-only reweighting baselines.
arXiv:2601.01616v2 Announce Type: replace
Abstract: The textile industry in Bangladesh is one of the most energy-intensive sectors, yet its monitoring practices remain largely outdated, resulting in inefficient power usage and high operational costs. To address this, we propose a real-time Non-Intrusive Load Monitoring (NILM)-based framework tailored for industrial applications, with a focus on identical motor-driven loads representing textile cutting machines. A hardware setup comprising voltage and current sensors, Arduino Mega and ESP8266 was developed to capture aggregate and individual load data, which was stored and processed on cloud platforms. A new dataset was created from three identical induction motors and auxiliary loads, totaling over 180,000 samples, to evaluate the state-of-the-art MATNILM model under challenging industrial conditions. Results indicate that while aggregate energy estimation was reasonably accurate, per-appliance disaggregation faced difficulties, particularly when multiple identical machines operated simultaneously. Despite these challenges, the integrated system demonstrated practical real-time monitoring with remote accessibility through the Blynk application. This work highlights both the potential and limitations of NILM in industrial contexts, offering insights into future improvements such as higher-frequency data collection, larger-scale datasets and advanced deep learning approaches for handling identical loads.
arXiv:2605.28661v1 Announce Type: new
Abstract: We present spin phase continuous modulation (SPCM), a new method for characterization of neutron beam properties. By utilizing spin-precession modulation induced by two oscillating magnetic fields, the method enables precise determination of neutron velocity and monochromaticity. We derive a theoretical formulation of the SPCM signal and experimentally validate it using measurements with a monochromatized neutron beam, obtaining reasonable agreement between experiment and prediction. SPCM enables quantitative determination of neutron beam velocity and monochromaticity.
arXiv:2605.22949v2 Announce Type: replace
Abstract: Foundation model agents increasingly operate in multi-agent deployments where a coordinator must decide which agent's response to trust. The standard approach weights agents by their self-reported confidence, but recent evidence shows that foundation model confidence is systematically miscalibrated and, on hard tasks, inversely correlated with accuracy. Design-time calibration methods (temperature scaling, Platt scaling, histogram binning) cannot address this problem because they fit a fixed correction to held-out data and degrade under distribution shift. We present MARGIN (Multi-Agent Runtime Grading via Incremental Normalisation), an online calibration method that learns per-agent, per-confidence-band calibration factors from the task stream itself, requiring no model access, no held-out data, and no retraining. MARGIN uses symmetric exponentially weighted moving averages with Bayesian shrinkage blending, and has three hyperparameters with robust defaults. Across 18 foundation models, 8 benchmarks, and over 44,000 observations, MARGIN achieves 3-6x lower calibration error than the best design-time baseline under distribution shift. In multi-agent selection, raw verbalized confidence fails to beat random at pairwise resolution (43-50%) on hard benchmarks. MARGIN corrects this completely, raising pairwise resolution to 70-89% and closing 37-78% of the Raw-to-Oracle pass@1 gap across the five code-generation benchmarks without any oracle knowledge of which model is strongest. Six formal propositions characterize convergence, tracking speed, and the optimality of symmetric updates for non-strategic agents, with all predictions illustrated empirically.
arXiv:2605.22705v2 Announce Type: replace
Abstract: We introduce Tokenization with Split Trees (ToaST), a subword tokenization method that directly optimizes compression under a new recursive inference procedure. ToaST greedily splits each pretoken into a full binary tree using precomputed byte n-gram counts, independent of any vocabulary. Given a vocabulary, inference recursively descends each split tree and emits the first in-vocabulary node reached on each path. Vocabulary selection is formulated as an Integer Program (IP) that minimizes the total token count over all split trees under this inference procedure. The Linear Programming (LP) relaxation is near-integral in practice, yielding provably near-optimal vocabularies, with training time empirically scaling quadratically in the number of split trees. On English text, ToaST reduces token counts by more than 11% compared to BPE, WordPiece, and UnigramLM at vocabulary sizes of 40,960 and above, reducing the number of inference tokens for models using this tokenizer, thus extending the effective context length. ToaST also uses common single-byte tokens less frequently than these baselines, leading to a substantial improvement in Renyi efficiency. In experiments training 1.5B parameter language models, ToaST achieves the highest CORE score, outperforming baselines by 2.6%--7.6%, with significance for two of three, and scoring best on 13 of 22 individual tasks.
arXiv:2605.22661v2 Announce Type: replace
Abstract: Trauma resuscitation is a clinical process for treating life-threatening physiological disorders in safety-critical environments, driven by the experience of healthcare workers (HCWs). Designing and optimizing quantifiable metrics that accurately capture HCW decisions may augment current resuscitation procedures with the potential to improve patient outcomes. This motivates our socio-technical formulation of trauma resuscitation as a distributed generalized Nash equilibrium (GNE)-seeking game with coupled inequality constraints. This method is optimized over a time-varying communication graph. We introduce novel insights from clinical experience to model HCWs behavior. This work facilitates the best possible resuscitation outcome given HCWs workloads, schedules, competencies, and limited resources.
arXiv:2605.25767v2 Announce Type: replace
Abstract: Synthesizing high fidelity contrast enhanced MRI is clinically valuable for safer and more efficient breast cancer screening, yet remains challenging due to complex lesion textures and heterogeneous enhancement patterns.
arXiv:2605.28060v1 Announce Type: new
Abstract: Explaining the predictions of neural models in clinical NLP remains a significant challenge, especially for complex tasks involving long, unstructured medical texts. While post-hoc methods like LIME and SHAP are widely used, they often fall short when applied to clinical narratives. In this paper, we identify core limitations of token-level and perturbation-based explanation techniques through targeted demonstra- tions on a hospital length-of-stay prediction task. Our findings reveal issues such as overemphasis on non-informative tokens, instability in at- tributions, and high-confidence predictions for incoherent input variants. These results underscore the need for explanation strategies that are clin- ically meaningful, semantically grounded, and robust to linguistic noise.
arXiv:2509.15848v2 Announce Type: replace
Abstract: Industrial monitoring systems, especially when deployed in Industry 4.0 environments, are experiencing a shift in paradigm from traditional rule-based architectures to data-driven approaches leveraging machine learning and artificial intelligence. This study presents a comparison between these two methodologies, analyzing their respective strengths, limitations, and application scenarios, and proposes a basic framework to evaluate their key properties. Rule-based systems offer high interpretability, deterministic behavior, and ease of implementation in stable environments, making them ideal for regulated industries and safety-critical applications. However, they face challenges with scalability, adaptability, and performance in complex or evolving contexts. Conversely, data-driven systems excel in detecting hidden anomalies, enabling predictive maintenance and dynamic adaptation to new conditions. Despite their high accuracy, these models face challenges related to data availability, explainability, and integration complexity. The paper suggests hybrid solutions as a possible promising direction, combining the transparency of rule-based logic with the analytical power of machine learning. Our hypothesis is that the future of industrial monitoring lies in intelligent, synergic systems that leverage both expert knowledge and data-driven insights. This dual approach enhances resilience, operational efficiency, and trust, paving the way for smarter and more flexible industrial environments.
arXiv:2605.28121v1 Announce Type: new
Abstract: Landscape feature representations play a central role in automated algorithm selection and meta-learning for black-box optimization, yet little is known about how different representations agree (or disagree) in the structures they impose on problem spaces. This paper presents a systematic unsupervised evaluation of four state-of-the-art representations (ELA, DeepELA, TransOptAS, and DoE2Vec) using a diverse set of affine combinations of BBOB functions (MA-BBOB). By applying extensive clustering analyses, coverage-based stability measures, and cross-representation similarity assessments, we show that each representation organizes the same problems in markedly different ways: ELA and TransOptAS form compact geometric structures, DeepELA provides a balanced intermediate view, and DoE2Vec achieves strong semantic alignment but with substantial fragmentation. Our results reveal that no single representation dominates; rather, they capture complementary aspects of the underlying landscapes. These findings highlight the importance of multi-view analyses for understanding representation behavior and offer guidance on selecting or combining representations in downstream meta-learning and algorithm selection tasks. In addition, across two different algorithm families (Differential Evolution and Particle Swarm Optimization), we show that landscape representations face an inherent trade-off in how well they align structural landscape descriptions with observed performance, indicating that no single representation can fully capture algorithm performance.
arXiv:2605.22166v2 Announce Type: replace
Abstract: LLM agents are shaped not only by their language models, but also by the runtime harness that mediates observation, tool use, action execution, feedback interpretation, and trajectory control. While existing agent adaptation methods mainly update model parameters, many failures in deterministic, rule-governed domains stem from mismatches at the model--environment interface. We propose Life-Harness, a lifecycle-aware runtime harness that improves frozen LLM agents without changing model weights or evaluation environments. Life-Harness evolves from training trajectories by converting recurring interaction failures into reusable interventions across environment contracts, procedural skills, action realization, and trajectory regulation, and remains fixed for evaluation on unseen tasks. On seven deterministic environments from $\tau$-bench, $\tau^2$-bench, and AgentBench, Life-Harness improves 116 out of 126 model--environment settings across 18 model backbones, with an average relative improvement of 88.5%. Harnesses evolved only from Qwen3-4B-Instruct trajectories transfer to 17 other models, showing that Life-Harness captures reusable environment-side structure rather than model-specific behavior. These results position runtime interface adaptation as a complementary alternative to model-centric agent training. Code is available at https://github.com/Tianshi-Xu/Life-Harness.
arXiv:2601.23262v2 Announce Type: replace
Abstract: We introduce a guided stochastic sampling method that augments sampling from diffusion models with physics-based guidance derived from partial differential equation (PDE) residuals and observational constraints, ensuring generated samples remain physically admissible. We embed this sampling procedure within a new Sequential Monte Carlo (SMC) framework, yielding a scalable generative PDE solver. Across multiple benchmark PDE systems as well as multiphysics and interacting PDE systems, our method produces solution fields with lower numerical error than existing state-of-the-art generative methods.
arXiv:2605.28059v1 Announce Type: new
Abstract: The parareal algorithm is a powerful parallel-in-time integration method that accelerates the numerical solution of evolution equations by iteratively combining a fine propagator and a coarse propagator. Although the convergence of the parareal algorithm has been extensively studied, most existing analyses assume that the fine propagator is either an exact solver or a single-step method. In this paper, we construct and analyze a parareal algorithm for solving parabolic equations, where the fine propagator is based on the two-step backward differentiation formula (BDF2), while the coarse propagator remains a single-step method. We propose a novel approach to design an effective correction for the initialization steps and establish linear convergence of the iteration. Numerical results fully support the theoretical findings, show clear improvements over existing multistep parareal strategies, and indicate that the proposed approach extends effectively to higher-order BDF methods and to nonlinear problems.
arXiv:2601.18006v2 Announce Type: replace
Abstract: We present PEAR (Pairwise Evaluation for Automatic Relative Scoring), a supervised quality estimation (QE) metric family that reframes reference-free machine translation (MT) evaluation as a graded pairwise comparison. Given a source segment and two candidate translations, PEAR predicts the direction and magnitude of their quality difference. The metrics are trained using pairwise supervision derived from differences in human judgments, with an additional regularization term that encourages sign inversion under candidate order reversal. On the WMT24 meta-evaluation benchmark, PEAR outperforms strictly matched single-candidate QE baselines trained with the same data and backbones, isolating the benefit of the proposed pairwise formulation. Despite using substantially fewer parameters than recent large metrics, PEAR surpasses far larger QE models and reference-based metrics. Our analysis further indicates that PEAR yields a less redundant evaluation signal relative to other top metrics. Finally, we show that PEAR is an effective utility function for minimum Bayes risk (MBR) decoding, reducing pairwise scoring cost at negligible impact.
arXiv:2605.28053v1 Announce Type: new
Abstract: Test-time training (TTT) adapts an LLM during generation by reading and updating request-owned state, such as fast weights, low-rank deltas, or streaming learner state. This breaks batched LLM serving, which assumes shared static weights: serial execution is correct but slow, while naive batching can corrupt request state. We formulate this problem as read-write TTT serving and present RW-TTT , which tags each decode step with its owner, version, and READ/WRITE effect, batches only compatible phases, and commits updates only to the owner. On one GPU with eight fast-weight InPlace-TTT streams, RW-TTT reaches 274.61 aggregate tok/s, 9.31x over sequential serving and 3.44x over per-stream replicas under the same memory budget. It preserves behavior on RULER, a long-context benchmark, and passes owner/version checks.
arXiv:2605.28058v1 Announce Type: new
Abstract: Recent work explored the capabilities of Large Language Models (LLMs) in Aspect-Based Sentiment Analysis (ABSA) through few-shot prompting, requiring substantially fewer annotated examples while achieving notable improvements over zero-shot baselines. However, a performance gap remained compared to models fine-tuned on hundreds of examples, and the computational costs of LLM inference present practical barriers to deployment. We introduce LLM-based Multi-View Prompting (LLM-MvP), which adapts the multi-view principle of considering multiple element orderings to LLM prompting. By combining schema-constrained decoding with a context-free grammar and prefix batching, LLM-MvP achieves performance competitive or superior to fine-tuned approaches while substantially reducing computational overhead. Extensive experiments across five benchmark datasets demonstrate that LLM-MvP closes the gap between few-shot prompting and fine-tuned models, offering a practical and efficient solution for ABSA.
arXiv:2605.28725v1 Announce Type: new
Abstract: This article evaluates AI-enabled influence operations in synthetic social networks through controlled simulations of narrative release, amplification, and counter-messaging. We measure exposure and belief change in agentic audiences, showing that amplification maximizes reach, counter-messaging shifts opinions most, and narrative release requires larger attacker footprints.