Papers

This paper investigates the use of Behavior Cloning (BC) for autonomous driving from a bird's-eye view (BEV) perspective in simulated urban environments. BC uses supervised learning to mimic expert driving behaviors. Previous works have applied BC in the CARLA simulator but did not fully address the challenges of traffic light compliance. Our approach enhances BC by integrating a kernel density estimator to adjust training sample weights based on action density, thereby improving the learning of rare but critical actions such as stopping at red lights and accelerating at green lights, specially in scenarios of scarce number of expert demonstrations. Using BEV inputs, which provide an abstract top-down view of the driving environment, our method simplifies the policy learning process. The trained convolutional neural network (CNN) outputs steering and acceleration actions based on these BEV inputs and additional state variables. Experimental results in the CARLA simulator demonstrate that our weighted BC method significantly improves driving performance, achieving higher route completion compared to standard BC. This weighted approach proved to be crucial in learning correct driving behaviors, particularly in test environments not encountered during training, highlighting its potential for enhancing autonomous vehicle navigation.

Large Language Models (LLMs) are increasingly deployed in multi-agent environments that produce unanimous agreement, both in intended interactions that need coordination and in unintended emergent interactions. Consequently, understanding how LLMs with competing incentives reach consensus is crucial to better interpret and design LLM collectives. We introduce an evaluation, based on the Network Consensus game, to assess the mechanisms driving this process. Here, a network of agents must agree on one of two colours to receive a payoff, but agents are offered different payoffs for the agreed colour. We vary components such as communication access and network structure and assess six open-source models and one closed model (ChatGPT 5.6-sol). We find that open-source LLMs reach consensus less often than humans in comparable experiments and only if messages are communicated across the global network. ChatGPT 5.6-sol, however, is able to reach consensus with communication limited to its neighbours and with no communication ability. This is achieved through lower stubbornness and higher majority-following tendencies, and by providing more information about its neighbours' states in messages. However, situating agents in a highly clustered graph reduces consensus, regardless of these traits, demonstrating that both system design and individual model traits drive collective outcomes.

Effective social interaction requires more than fluent responses: agents must reach plans that fit the participants' needs and circumstances. Existing evaluations of social agents mainly rely on LLM judges that rate the conversation, without checking the resulting plan. We introduce HICO-Bench, a benchmark of 180 everyday coordination scenarios, such as resource allocation, scheduling, and authorization, in which two agents with private information converse and then independently record the plan they agreed on. A program checks Feasibility (the two records match and satisfy both participants' private conditions), and an LLM judge checks Integrity (the conversation supports the recorded plan); passing both is a Verified Success. Each scenario has two versions that share the same public context but differ in one private condition, so the correct plan differs between them. Across thirteen LLMs, 36% of conversations rated highly for goal completion fail Verified Success. To learn from outcomes that arrive only at the end of a conversation, we propose Paired-Credit Policy Optimization (PaCPO). After each turn, PaCPO asks the agent for a tentative plan, checks it in both versions of the scenario, and rewards the turns after which the tentative plans fit their respective versions. PaCPO raises Qwen3-8B's Verified Success from 20.4% to 28.3%.

Software engineering agents have advanced rapidly, but scaling their training remains constrained by the limited availability of high-quality executable tasks. Development histories contain valuable signals for constructing such tasks, yet they often require substantial reconstruction due to incomplete environments, missing tests, and inconsistent artifacts. We present SWE-Stream, a system for scaling executable SWE training data through progressive construction and elastic streaming execution. SWE-Stream progressively validates and refines task candidates, reusing existing artifacts when possible and applying targeted completion only when necessary. An elastic scheduler asynchronously coordinates construction stages under shared resource constraints, adapting execution budgets based on observed workload demands. Using development histories from 10,728 repositories across six programming languages, SWE-Stream constructs 80,874 validated tasks and collects 118,688 successful trajectories. Fine-tuning Qwen3-30B-A3B-Thinking-2507 on these trajectories achieves resolve rates of 69.0%, 49.3%, and 45.42% on SWE-bench Verified, Multilingual, and Pro, respectively. In a controlled comparison with approximately matched training budgets, SWE-Stream achieves a 45.6% resolve rate on SWE-bench Verified, outperforming three existing data sources. Moreover, its streaming construction strategy improves efficiency, delivering $1.45\times$ the accepted-task throughput of batch construction and accepting 13.2% more tasks than fixed-limit streaming.

Medication recommendation (MR) is critical for clinical decision support. While existing MR methods are mostly designed for single-center learning, where only one independent hospital is involved, multi-center MR with hospitals of different scales has become increasingly demanding in practice. In multi center settings, abundant data from large medical centers can improve recommendation performance for low-resource centers. Despite a few preliminary attempts on this task, two critical gaps remain. Gap 1: Existing multi-center methods fail to disentangle transferable cross-hospital clinical experience from hospital-specific prescribing patterns, limiting clinical feasibility and physician acceptance. Gap 2: They commonly overlook multi label safety constraints of MR, including drug-drug interaction risks and local formulary feasibility, which are essential for safe real-world deployment. To address these gaps, we propose HEM-Med, a novel hierarchical agentic memory framework for multi-center MR. To address Gap 1, we design a disentangled hierarchical memory module that builds patient-level medication context attribution records and disentangles them into cross hospital experience memory and hospital-specific residual memory. To address Gap 2, we introduce a safety-aware medication set generation module, which integrates dual-level experience retrieval with safety-aware set decoding to produce clinically relevant, safer, and locally adaptive medication recommendations. Experiments on a real-world multi-center eICU dataset show that HEM-Med outperforms representative transfer learning, LLM-based, and MR baselines in terms of both recommendation accuracy and safety.

Drifting models have emerged as a highly efficient and stable paradigm for policy design in offline reinforcement learning (RL). However, standard drift policies determine repulsion solely from geometric relationships among generated actions and therefore cannot distinguish them by expected value. To address this limitation, we introduce Value-Guided Repulsion Q-Learning (VRQL) to integrate action value estimates into the particle interaction field. For each state, VRQL combines geometric kernel distance with a normalized Q value scaling. This mechanism assigns greater repulsive influence to particles with lower values while strictly retaining attraction toward behavior action. Consequently, this value-guided interaction field aligns behavior regularization with policy improvement without adding an auxiliary behavior model stage. On 50 OGBench task configurations and 6 D4RL AntMaze configurations, VRQL demonstrates highly competitive performance against established baselines, suggesting that value-guided particle interaction is an effective method for offline RL.

Symmetry of Information (SoI) [ZL70] is a fundamental theorem of classical Kolmogorov complexity whose status for time-bounded computation is closely related to central open problems in complexity theory and cryptography. In a recent development, [HMO26] showed that SoI fails for $rKt$ complexity, namely in the setting of randomized computation. By contrast, many basic properties of Kolmogorov complexity are known to remain valid in the presence of nondeterminism [HLO26], suggesting that SoI may provide a fruitful structural principle for exploring the relative power of randomness and nondeterminism in computation. Our results reveal that the validity of SoI for nondeterministic computation, namely for $nKt$ complexity, is a subtle question connected to several frontiers. We show that symmetry of information holds on average for randomized extensions of $nKt$, while its worst case validity would imply breakthrough complexity separations. Although the standard cryptographic argument for asymmetry does not extend to the nondeterministic setting, we provide evidence that information remains asymmetric in nondeterministic computations. Among other results, we show that SoI would imply a collapse of exponential time classes to low levels of the polynomial hierarchy. Then, building on the work of [Hir22b, GK22, KK26, HMO26], we develop a general framework connecting symmetry of information, meta-complexity, and explicit constructions in the nondeterministic setting. More precisely, we prove that suitable formulations of these three notions are quantitatively equivalent. We apply different aspects of this correspondence to make progress on complexity lower bounds and on the failure of SoI for nondeterministic computation. These consequences are unconditional and provide some of the strongest known lower bounds in meta-complexity.

Tracking changing comparators is a central problem in online learning. For exp-concave losses, previous work established the $T^{1/3}P_T^{2/3}$ dependence on the horizon $T$ and Euclidean path length $P_T$ for fixed dimension, while the optimal cost of dimension remained unresolved. We resolve this question by establishing a sharp $d^{1/3}$ curved dimension factor, improving the $d^{2/3}$ factor of recent switching and interval reductions [1, 2]. To achieve this improvement, we develop a proper, full-information learner on compact convex subsets of $\mathbb{R}^d$ that adapts to the unknown path length and, under fixed dimension-independent diameter, gradient, and curvature parameters, guarantees $$\operatorname{Reg}_T(u_{1:T}) \le \widetilde{O}\left(d+\min\left\{d^{1/3}T^{1/3}P_T^{2/3},\sqrt{TP_T},T\right\}\right).$$ A matching lower bound on a diameter-one Euclidean ball establishes the minimax frontier up to logarithmic factors when $T\gtrsim d^2$, including the transition from the curved rate to larger path budgets. The lower bound already holds for losses that depend on only one coordinate per round, isolating an unavoidable cost of learning across directions. Our upper bound follows from square-root Gaussian KL control of comparator movement and a cancellation argument that pays for history restarts. The curved learner maintains $O(\log^2 T)$ Gaussian states, uses one gradient per round, and runs in time near-linear in $T$ under a Mahalanobis-projection oracle.

Skills are widely assumed to play a central role in career transitions, motivating their use in career path prediction (CPP) systems. In this work, we critically examine whether explicit skill representations provide complementary signal beyond text-based job representations. We evaluate multiple strategies for incorporating skills into CPP models, including score fusion and neural architectures, under two conditions: predicted skills and ground-truth ESCO annotations. Surprisingly, across two benchmark datasets, none of these settings yield substantial improvements over strong text-only baselines. Even when using ground-truth skills, gains remain marginal and inconsistent. Through detailed analysis, we identify key factors underlying this result: high redundancy between textual and skill representations, limited discriminative power of ESCO's taxonomy, and representational collapse in skill embeddings. Furthermore, we find that skill prediction difficulty correlates with overall sample difficulty, limiting the potential for complementary signals. Our findings challenge the common assumption that explicit skill modeling inherently benefits career prediction and suggest that dense text representations already capture most skill-relevant information.

Voice-based conversational agents are increasingly deployed in real-world settings, where environmental noise often degrades the interactive experience. Therefore, robust acoustic adaptability is essential to maintain natural and intelligible human-computer communication. However, most existing systems remain acoustically insensitive and fail to emulate the human Lombard effect, in which speakers involuntarily adjust their vocal production to preserve intelligibility in the presence of noise. As a result, their communicative reliability degrades under adverse acoustic conditions. To remain intelligible in noisy environments, conversational agents require a mechanism to emulate noise-induced adaptive behavior during synthesis. We propose NIL-TTS, a noise-induced Lombard TTS framework. We integrate a feature-wise linear modulation (FiLM) mechanism into a flow-matching backbone for dynamic vocal adaptation. A two-stage training paradigm is utilized: initial supervised fine-tuning on paired Lombard corpora, followed by Flow-GRPO post-training to optimize for intelligibility. Evaluations confirm that NIL-TTS autonomously adjusts its output in response to varying noise conditions, exhibiting key correlates of the human Lombard effect. Driven by these adaptive modulations, the synthesized speech achieves significant intelligibility improvements that scale proportionally with noise intensity. Ultimately, this work presents a flow-matching and reinforcement learning-based advancement within the adaptive Lombard speech synthesis paradigm for challenging real-world scenarios.

Probes on activation vectors are widely used to detect misbehavior in language models, but their success relies on the assumption that models cannot control what their activations encode. Humans can learn, through neurofeedback, to control the firing of even single neurons, and recent studies investigated whether this ability extends to language models, reaching conflicting conclusions. No experimental design so far disentangles competence at the task from genuine access to one's own activations. We fill this gap with in-context neurofeedback sessions, in which a "subject" model is asked to maximize (or minimize) a score derived from its activations, shown back to it at every turn. In our first experiment, the sentences are generated either by the subject or by a second "writer" model, while the score always derives from the activations of the subject. We test ten open-weight models from five families, with sizes from 9B to 32B. Some models move their own scores considerably, but no more than a writer of comparable competence moves them. Is this because the task requires no privileged access, or because the subject controls its activations while processing the sentences, whoever wrote them? To answer this, we prefill a fixed sentence as the subject's reply at every turn and ask it to increase or decrease the score. Three out of ten models show small but consistent control effects. We further ask whether models can control their activations to the point of fooling an activation monitor. We make models repeat sentences a monitor would flag, such as a deceptive answer for a deception monitor, and ask them to raise or lower the monitor's score. No model learns to lower it, but one model can raise it. In-context control of a model's own activations might not yet be a threat to activation monitors, but it exists in a few models and needs to be tracked as models evolve.

We study Boolean entropy and Fisher information in information inequalities and the Boolean central limit theorem. We prove a fractional Stam inequality for the Boolean Fisher information associated with arbitrary fractional partitions of subset sums, and derive an entropy power inequality for sums of Boolean independent random variables and its weighted version. We then establish a Boolean analogue of Barron's entropy convergence result along the Boolean central limit theorem: Boolean entropy converges to the entropy of the Rademacher law if and only if the initial entropy is finite. Furthermore, under a finite fourth moment, in the Boolean central limit theorem, we obtain \[ \Gamma(\mu_n\mid\mathbf b)= \frac{m_4(\mu)-1-m_3(\mu)^2}{2}\frac{\log n}{n} +o\!\left(\frac{\log n}{n}\right), \] with an explicit example showing sharpness. For symmetric laws with finite fourth moment and finite Boolean Fisher information, \[ \Psi(\mu_n\mid\mathbf b) =2\bigl(m_4(\mu)-1\bigr)\frac{\log n}{n} +o\left(\frac{\log n}{n}\right). \] Our approach is based on the Nevanlinna representation of Cauchy transforms.

Parallel drafters such as DFlash and DSpark reduce proposal latency, but early mismatches limit how much of each block can be accepted. Retaining alternatives introduces parent states and candidate choices that reference-conditioned training does not directly supervise. We introduce TreeSpark, a unified training and inference framework extending the semi-autoregressive DSpark architecture. It constructs parent-conditioned candidate trees from one backbone pass and replays their expansion, pruning, and budgeted packing during training. Survival negative log-likelihood weights retained edges by reference-derived path mass, while a capped coverage hinge promotes target-important alternatives near local selection boundaries. Both objectives reuse reference-chain target distributions without additional target forward passes. We evaluate greedy decoding with Qwen3-4B and Qwen3-8B on nine general benchmarks and six writing domains. Across targets and suites, TreeSpark improves mean acceptance length over DSpark by 23.4% to 31.6% and mean single-request throughput by 15.1% to 25.0%. Batched Qwen3-4B throughput improves by 12.6% to 17.2%. At fixed attention capacity and inference policy, the proposed supervision further improves mean acceptance length by approximately 6.4% and mean system throughput by 4.2% to 5.0% on Qwen3-4B.

Reinforcement Learning on Mixed-domain preference data (Mix-RL) has become the mainstream approach for training general-purpose Generative Reward Models (GRMs). However, Mix-RL suffers from two critical bottlenecks: the reward sparsity induced by outcome rewards, and the cross-domain interference arising from jointly optimizing heterogeneous capabilities, which together give rise to imbalanced capability acquisition and pervasive reward hacking. Inspired by the success of On-Policy Distillation (OPD) in multi-domain capability integration, we introduce RM-OPD (Reward Modeling via On-Policy Distillation), a two-stage framework that separates specialist acquisition from capability integration. First, we cultivate domain-specialized teacher models via single-domain GRPO fine-tuning, allowing each expert to reach its performance ceiling in isolation; then we consolidate these teachers into one student model through (i) routed on-policy distillation, which provides dense signed token-level supervision on student-generated critiques; (ii) domain contribution reweighting, which reweights token guidance toward target domain shares, preventing specific domains from dominating optimization; and (iii) optional criteria context distillation, which conditions teachers on domain-specific evaluation criteria to sharpen token-level supervision. Across multiple RM benchmarks and two base models, RM-OPD consistently outperforms vanilla Mix-RL and other strong baselines, achieving overall superior performance and exhibiting an emergent "teacher-surpassing" effect. These results establish RM-OPD as a promising paradigm for building generalist GRMs.

Bosley and Dodis (TCC 2007) proved that a class of imperfect randomness sources that suffices for information-theoretic encryption of messages longer than the logarithm of the key length must admit deterministic extraction of nearly uniform bits, and asked whether the same is true of two-out-of-two secret sharing. Aggarwal, Chung, Obremski, and Ribeiro (TCC 2022) gave a positive answer for schemes that are in addition leakage-resilient or non-malleable; the original question remained open. We answer it in the negative. For every $b\ge2$ we construct a class of flat sources on $\{0,1\}^{b+2}$, each of min-entropy at least $b$, together with a perfectly correct and perfectly private two-out-of-two scheme that shares a $b$-bit secret into two $(b+1)$-bit shares using any source in the class, and we show that every deterministic map from $\{0,1\}^{b+2}$ to $\{0,1\}$ is at statistical distance at least $1/6$ from uniform on some source in the class. This implies that sharing a long enough secret does not require extractable randomness. The proof is a short parity argument. The idea of the construction extends to other thresholds: for two-out-of-$n$ and $r$-out-of-$r$ sharing we give perfect schemes with $(b+1)$-bit shares, private for classes of flat sources from which no single bit can be extracted with error below $1/(4n-2)$ and $1/(2(2^r-1))$, respectively.

Full-duplex speech systems must decide when to enter, hold, or relinquish the conversational floor, even as multiple speakers overlap or backchannel without taking it. Existing evaluations study dyadic turn-taking or end-to-end agent behavior, but lack a unified, controlled evaluation of genuine floor transitions against confusable non-events in multi-party settings. We introduce MultiPartyTurnBench (MPTB), a benchmark of 240 synthetically generated, channel-separated conversations spanning two to five speakers and six interaction types. MPTB evaluates two complementary tasks: End-of-Turn (EOT) detection distinguishes genuine turn completion from temporary holds, while Interruption (INT) detection distinguishes successful floor takeovers from non-floor-taking speech. Exact event-conditioned annotations enable causal evaluation using false-positive-constrained recall and signed latency. Across acoustic, semantic, and turn-projection baselines, we find a stark asymmetry: learned systems achieve 82.5-92.6% EOT recall at 4.3-11.8% false-positive rates, while INT detection suffers from missed takeovers or excessive false activations. This asymmetry extends to five full-duplex agents which achieve 86.1-95.8% balanced accuracy on turn entry, yet perform near chance (46.9-54.7%) on selective interruption handling. Gemini-3.8-Live yields to 97.7% of backchannels, whereas MiniCPM-o-4.5 yields to only 1.4% of genuine interruptions. These findings establish selective floor control as a distinct, unresolved challenge for reliable multi-party voice interaction.

Constant-time execution is an important security property, especially for IoT devices, that prevents the leakage of sensitive information over timing side-channels. However, achieving constant-time execution is very hard when going down to the cycle level, at least on realistic devices. A lot of research is concerned with producing tools that either determine whether code is constant-time or that ensure it is compiled into a constant-time binary, with various degrees of accuracy. In this work, we present and evaluate a full workflow for hardening against timing side-channels during compilation. It starts with taint analysis to determine the code locations that depend on sensitive information. These are then the object of automated control-flow transformations inside the compiler to seal possible timing side-channels. We evaluate our workflow in detail on a realistic application running on a RISC-V core using both static timing analysis and statistical methods. Even though we do not reach cycle-accurate constant-time execution, our statistical results suggest that our hardened binary is safe against timing attacks.

We study the problem of learning accurate and cognitively simple binary classifiers that are directly interpretable as Boolean rules. We propose mixed integer linear programming (MILP) formulations for training sparse disjunctive normal form (DNF) networks, viewed as small networks with a conjunctive hidden layer and a disjunctive output layer. Contrary to previous work that uses MILP for inductive rule learning, we start with a fixed network structure, for which we then find optimal weights. A regularized objective explicitly trades off misclassification costs against sparsity, yielding globally optimized rule sets. Our main technical contribution is an enhanced formulation that substantially reduces the number of integer decision variables and eliminates redundant constraints, while preserving exact Boolean semantics for all feasible solutions. Furthermore, we develop a combined approach based on initialization and dropout to break symmetries in the weights between rules, mitigating redundancy, and encouraging more diverse and stable rule representations. Experiments on synthetic benchmarks and UCI datasets show that the advanced formulation improves computational efficiency and achieves competitive or superior accuracy compared to established interpretable baselines, including SAT-based DNF learning and well-known rule- and tree-based learners. Overall, our approach provides a principled optimization framework for learning compact Boolean rule sets with explicit control over accuracy and sparsity trade-offs.

Language models often produce semantically similar answers to open-ended questions, even when many plausible alternatives exist. Generating useful alternatives requires identifying both what the query calls for and what existing responses already cover. We introduce Gap Detection, a framework that searches for relevant but unoccupied directions in a shared text embedding space. Its objective, GapScore, combines query relevance (Demand) with dissimilarity to the nearest existing item (Defensibility). The framework optimizes this product on the unit sphere, maps candidate directions to concept words with a language model, and uses task-specific filtering and constrained prompting to turn those concepts into text. On five curated topics and 90 INFINITY-CHAT queries, the reported mean relative reductions in output Collision are 12.8% and 10.8%, respectively. We also instantiate the framework for generative engine optimization over four product markets and for iterative synthetic-data augmentation. In the latter setting, with 100 training examples per method, Gap Detection reduces Collision from 0.324 to 0.298 relative to undirected accumulation and increases the Vendi Score from 27.16 to 29.20; the accuracy difference is one example on a 40-example test set. Component ablations expose the trade-off between semantic separation and relevance, while also showing that better direction scores do not uniformly yield better downstream metrics. These results support explicit gap search as a practical mechanism for diversifying content, with task validity checked separately from geometric novelty.

This pictorial presents The Body in Algorithmic Colonialism, a screen-based interactive installation that critically examines Emotion-AI through artistic practice. The work uses facial tracking to simulate how commercial Emotion-AI systems translate facial movement into emotional categories and verdicts of compliance or non-compliance. Rather than treating explainability as technical transparency alone, the installation approaches XAI as an embodied encounter with misrecognition: viewers experience how the body is measured, classified, and returned to itself through algorithmic thresholds. Drawing on critical AI studies, affect theory, and practice-as-research, the pictorial positions artistic practice as a method for making affective classification visible and contestable. It documents the conceptual framework, technical process, and critical context of a prototype developed in the first year of a practice-based PhD. No audience responses, interviews, or participant data are analysed in this submission.

Learning world models across diverse domains calls for a unified control space, yet ac- tion interfaces vary across domains and action annotations are often scarce. Latent ac- tions learned directly from videos offer a promising way to establish such a space without explicit action supervision. However, learning shared latent actions across domains re- mains challenging, as variations in appearance, embodiment, and dynamics can entangle domain-specific visual cues with transferable transition structure. To this end, we intro- duce OneLA, a simple framework that learns continuous latent actions through a shared orthogonal dictionary and a common predictive objective, without task-specific designs or cross-domain alignment losses during latent action pretraining. These latent actions pro- vide a shared conditioning interface for world models, with lightweight adapters mapping native control commands into the same space. Conditioned on latent actions and the cur- rent visual state, the world model predicts context-dependent transitions for controllable rollout. OneLA improves action readout across domains and reduces action cycle-transfer rotation error by 24.8% over the strongest evaluated baseline. A joint-training comparison further shows a 20.5% improvement in Human Preference Score v3 (HPSv3) for real- scene generation. These results suggest a path toward general-purpose world models that learn from diverse videos and support flexible control through latent action space.

Self-supervised joint embedding learning aligns representations of augmented views while regularizing their distribution to prevent collapse. Regularization aims to shape the overall representation distribution, but most joint embedding methods restrict its computation to the active minibatch. We propose out-of-batch regularization, which maintains a dataset-level state in CPU memory and uses globally constructed per-instance targets during minibatch training. Evaluated on natural images and biomedical datasets, these anchors approximate the full-dataset regularization gradient more faithfully than conventional minibatch estimation at small batch sizes. Applications to contrastive (SimCLR) and non-contrastive (SIGReg) approaches show consistent improvement over the corresponding in-batch objectives for image classification, minority-class performance under controlled imbalance, instance retrieval, and continued self-supervised pretraining, with the largest gains at small batch sizes. These results suggest that dataset-level regularization can be decoupled from minibatch optimization, making batch size an optimization choice that does not affect the geometry of the regularizer.

World Action Models (WAMs) typically adapt video foundation models to robotic control through joint video and action prediction. However, task-level instructions may leave the next physical interaction underspecified, requiring semantic grounding and state-dependent motion selection. To this end, we introduce Atomic-WAM, an understand-then-execute framework that connects task reasoning to action generation through atomic-motion descriptions. Specifically, a vision-language reasoner describes the next local motion from the task instruction and visual context, guiding a WAM to predict future video and an action chunk. Furthermore, an automatic annotation pipeline curates temporally aligned, contact-enriched supervision from multi-view DROID demonstrations. To make atomic-motion predictions executable by the WAM, we post-train the reasoner with Execution-Grounded GRPO (EG-GRPO). With the WAM fixed, EG-GRPO adapts the reasoner through rewards for motion appropriateness and execution success. Finally, Atomic-WAM achieves 39.6% task success under default instructions and 31.6% under vague instructions in a real-to-sim evaluation on RoboLab. Project page: https://ssj9596.github.io/Atomic-WAM-project

Banks rely on extensive internal policy frameworks to ensure that corporate lending decisions comply with regulatory requirements and internal risk standards. Reviewing loan applications against these policies is a largely manual and knowledge-intensive process, which can lead to overlooked policy violations or exceptions. This report presents a prototype of an LLM-based policy checker that automatically verifies loan applications against internal lending policies. The proposed approach follows a two-step architecture. First, compliance-relevant rules are automatically extracted from policy documents and converted into structured, machine-readable representations. Second, loan applications are evaluated against the extracted rules to identify policy exceptions, non-compliant findings, missing information, and cases requiring manual review. Evaluation results demonstrate that the rule extraction process is highly stable across multiple runs and consistently captures rules identified as critical by a domain expert. When evaluated on 11 real loan applications with known policy exceptions, the system successfully detected the majority of these exceptions and identified additional compliance issues that had previously been overlooked during manual reviews. While the approach produces false positives and cannot fully replace human judgement, the results indicate that LLM-based policy compliance verification can provide valuable support in the loan application verification process by highlighting potential compliance risks.

Robotic vacuum cleaners must extend their functionality within tight limits on size, cost, and durability. Deployable linkages with few actuators meet these limits, but their backdrivability makes it difficult to hold a load-bearing posture without continuous motor torque. We introduce a two-stage deployable linkage that is self-locking, in the sense used for toggle and singularity-based linkages, through its own geometry: at full deployment an internal three-link subchain approaches a collinear, near-singular configuration where the input–output transmission ratio approaches zero, so that plate loads produce a small residual back-driving torque, absorbed by drive-train friction and a lightweight magnetic detent. A single actuator performs deployment and locking, a passive chassis-mounted trigger releases the lock for retraction, and a second actuator adjusts only the deployment height. We integrate the mechanism into a commercial robotic vacuum cleaner and validate it through a 100-cycle repeatability test, a quasi-static load test in which the locked plate held 50\,N with the motor de-energized, and 140 pushing-type tidying trials on seven household objects against a commercial arm-equipped vacuum robot under a documented protocol. We derive the analytical holding condition and discuss its limits as an intermediate design point between passive compliance and articulated manipulation.

We propose and analyze a projection-based model reduction method for the rapid and reliable solution of time-harmonic acoustic wave propagation problems over a frequency band, with particular emphasis on seismic applications. The high-fidelity model is based on a hybridizable discontinuous Galerkin (HDG) discretization, formulated as a generalized saddle-point system coupling the volume and trace unknowns. The basis construction combines residual-based greedy sampling of the frequency parameter, enrichment with frequency derivatives of the HDG solution, and proper orthogonal decomposition (POD) compression. We establish the well posedness of both the high-fidelity and reduced problems and characterize their stability with inf-sup constants. We investigate the interaction between static condensation, inherent to the HDG discretization, and projection onto the reduced spaces, characterizing its implications for the reduced formulation and approximation errors. Since these operations do not commute in general, we derive a priori error estimates for both the trace and volume variables to quantify the gap between the two operations. We further identify a lifting condition on the volume reduced space that eliminates these gaps and yields a trace error estimate independent of the volume approximation error. Numerical experiments on the two-dimensional Marmousi model and a three-dimensional heterogeneous medium, with more than $10^{7}$ unknowns, illustrate the theoretical estimates and show that the reduced model achieves speedups of several orders of magnitude compared to the high-fidelity solver.

News outlets in poorer countries cover the world much as the leading outlets of rich countries do. Two explanations compete. One says they depend on Western news agencies for lack of resources. The other says they choose to copy prestigious outlets or whoever moves first. Observation cannot tell these apart. This study measured how closely 18 national outlets in Bangladesh, Kenya, South Africa, India, Malaysia and Nigeria followed four core outlets in how much attention they gave, which angle they took and when they published, on the wars in Ukraine and Gaza and two UN climate conferences in 2022-2024. It then ran a simulation in which language models acted as the outlets' editors and dependence, imitation and herding were switched on and off. Of nine tests, one held: outlets that relied more on wire copy published sooner after the core did. Tier and local stake showed no effect distinguishable from none. The herding test was supported and the imitation test was not. The simulation did not decide between the mechanisms, because the dependence rule, as fitted, reduced to publishing wire copy. Wire copy sets the clock of the periphery's foreign news. Whether it sets the agenda stays open.

In various industries, smoke and fire are two of the most important threats in the workplace. One of the common methods for detecting smoke and fire is the use of infrared thermal and smoke sensors, which cannot be used in outdoor applications. Therefore, the use of vision-based methods seems necessary. The problem of smoke and fire detection is spatiotemporal and requires spatiotemporal solutions. This paper presents a method that uses spatial features along with temporal-based features to detect smoke and fire in the scene. It consists of three main parts; the task of each part is to reduce the error of the previous part so that the final model has a robust performance. This method also uses transformer modules to increase the accuracy of the model. The results of our model show the proper performance of the proposed approach in solving the problem of smoke and fire detection and can be used to increase workplace safety.

We give a randomized polynomial-time $0.48$-approximation for maximizing a nonnegative non-monotone $k$-submodular function under a matroid constraint, for every $k\ge2$. The algorithm combines a top-two label rule with a nested-chain potential and maximum-weight matroid bases. Its analysis reduces the approximation guarantee to a one-dimensional time allocation: a uniform local lower bound leads to a linear differential equation, concavity closes the remaining interval, and two elementary budgets complete the proof. A strict saving in the time budget absorbs sampling and discretization errors, yielding the exact $0.48$ guarantee in the value-oracle model.

Sparse autoencoders (SAEs) have emerged as a promising approach to mechanistic interpretability by decomposing language-model activations into sparse, potentially interpretable features. However, differences in design assumptions, evaluation objectives, and experimental settings complicate conclusions about their effectiveness. We present a critical survey of 138 studies on SAEs in natural language processing. Our contributions are fourfold: (1) we propose a task-grounded taxonomy connecting dictionary design, feature operations, and NLP functions; (2) we examine how sparsity allocation, geometry, data coverage, and inference affect feature recoverability; (3) we assess evidence for semantic interpretability, mechanistic faithfulness, and behavioral utility; and (4) we synthesize findings across multilingual processing, retrieval, reasoning, classification, and behavioral regulation, highlighting the roles of objectives, baselines, supervision, and intervention pipelines. Through comparative analyses of published results, we reconcile apparent disagreements, identify unresolved questions, and propose directions for more rigorous evaluation. An anonymous research register https://anonymous.4open.science/r/sae-research-register-C331/register.html accompanies the survey.