Science & Mathematics

Fast and reliable manipulation is crucial for practical robot deployment. Although Vision-Language-Action (VLA) models have recently shown remarkable progress as generalist robot policies, their execution often remains temporally inefficient. A key source of this inefficiency is that policies learn fine-grained temporal patterns from teleoperated demonstrations, requiring many low-level action steps. Temporal action quantization offers a simple way to accelerate execution by aggregating consecutive low-level actions into temporally coarser actions. However, applying action quantization without considering when fine-grained control is required introduces a speed-accuracy trade-off: accelerated actions may efficiently reduce redundant steps in some phases, while discarding critical motion details in precision-sensitive interactions. To address this, we propose PaceVLA, a unified framework for adaptive temporal execution in VLAs that integrates two coupled components: (1) mode-specific action decoders built on a shared action expert, supporting multiple temporal granularities and prediction horizons, and (2) a quantizability-guided mode selection scheme which decides whether coarse execution is appropriate, and a context-conditioned router that selects an execution mode at each inference step. Experiments across three multi-task simulation benchmarks and six real-world tasks show that PaceVLA improves execution efficiency while maintaining task success rate across multiple embodiments, including long-horizon and dexterous manipulation.

Passive-wheel quadrupedal robots offer energy-efficient locomotion through leg-driven propulsion and momentum-driven gliding. However, navigation requires coordinating steering with intermittent propulsion and adapting push-glide timing to task demands. Velocity-tracking objectives may suppress the speed variations inherent in skating, discouraging efficient gliding. To address these challenges, we propose SkateNav, a unified skating-navigation framework based on reinforcement learning. A time-budgeted goal-reaching objective allows the policy to jointly learn steering, propulsion, and their temporal allocation. An adaptive skating cycle structures gliding, pushing, and recovery, while frequency modulation at every control step adjusts phase durations to navigation demands. Simulation experiments demonstrate higher average success rates and lower cost of transport than the evaluated planner-controller baselines, with ablations confirming the contributions of cycle structure and frequency adaptation. Real-world experiments demonstrate zero-shot transfer from simulation to a passive-wheel Mini Cheetah across cluttered indoor spaces, slopes, and paved outdoor surfaces. Supplementary videos are available on the project page: https://ktw1404.github.io/SkateNav/

Judgment models answer semantic questions by scoring a finite set of candidate outcomes. Can reusable programs turn these local decisions into powerful multistep reasoning? We introduce \method, a framework that jointly constructs judgment schemas and composition programs for frozen judgment models. A generative teacher designs the procedure offline; the judgment model resolves local semantic questions online, and the saved program composes its decisions into an answer. We study three allocations of design effort between humans and the teacher, focusing on construction through a shared interface. We instantiate the framework with Kev. On three selected BIG-Bench Hard tasks, nine independently constructed programs solve all 450 executions of 150 development inputs. A separate deployment study freezes three programs after development-set reference-agreement refinement and evaluates them on 600 held-out questions. These programs achieve near-perfect 99.67\% macro accuracy, versus 64.00\% for direct Kev and 68.80\% for final-answer-only Qwen3.5-4B. They attain comparable observed accuracy to Qwen's unrestricted response policy (99.07\%) with an \textbf{8.43-fold online speedup}: 0.255 versus 2.150 seconds per question. These results show how reusable programs can substantially expand the reasoning capability of a compact judgment model while keeping its parameters fixed.

We set out to reproduce a recent hallucination-mitigation result on the POPE benchmark. The LLaVA-1.5-7B baseline we measured, 82.21 F1 on the adversarial split, sat 1.21 to 8.67 points above the adversarial baselines we planned to compare against (81.00, 79.30, and 73.54). We looked at the evaluation code and found a readout choice that moves F1 on its own. A two-token logit readout decides yes versus no by comparing two vocabulary IDs, 3582 ("yes") and 1217 ("no"). Across 9,000 greedy-decode questions spanning all three splits, neither ID is generated even once. The model emits " Yes" (token 3869) and " No" (token 1939), because SentencePiece prepends a space byte after the prompt suffix "ASSISTANT:". Read with an eight-token lookup that covers the space-prefixed surface forms, LLaVA-1.5-7B scores F1 0.8221, 0.8498, and 0.8713 on the adversarial, popular, and random splits. That 6.13-point adversarial shift exceeds the adversarial gain reported by five of the six papers we surveyed. None of them states its readout, and our reference ran under 4-bit NF4 quantization, so we cannot say how much of any reported gain a matched evaluation would keep. That comparison stays unresolved until readout and precision are matched. On the fixed baseline we run nine inference-time corrections of our own (none beat it) and dissect why the adversarial split resists logit-level intervention. In a 3,000-question probe, wrong predictions draw more image attention than correct ones (Cohen's $d=-0.46$, $p=1.4\times10^{-24}$), the opposite of what grounding-based corrections assume. A four-readout audit across four further VLMs from three tokenizer families confirms the confound is protocol-level, not model-specific: porting the LLaVA-1.5 IDs verbatim drops F1 to 0.00 on the two disjoint-vocabulary models, whereas a tokenizer-derived readout holds between 0.80 and 0.92.

Ferrimagnetic oxides such as rare-earth iron garnets (REIG) have emerged as essential components of spin-based devices owing to their high Curie temperatures, low Gilbert damping, and excellent insulating properties. Recently, REIGs have attracted immense interest for hosting robust chiral spin textures that can be potential information carriers in next-generation spintronic devices. Here we investigate the structural, chemical, and magnetic behaviour of single-crystal Lu3Fe5O12 (LuIG) thin films for different film thicknesses on a Gd3(Mg,Zr)Ga5O12(111) or SGGG(111) substrate. Our results demonstrate the presence of a 3 nm-thick Gd-rich LuIG layer at the LuIG/SGGG interface, which gives rise to a magnetic compensation temperature around 50 K. We further probe the anomalous Hall effect (AHE) in LuIG layers with an adjacent platinum ultrathin film. In addition to the magnetic compensation point, the AHE loops show pronounced nonmonotonic features, often attributed to the spin Hall topological-like Hall effect (SH-THE) and non-collinear spin textures arising from the Dzyaloshinskii-Moriya interaction (DMI). LuIG thickness-dependent AHE measurements reveal that the composition variation due to Gd diffusion breaks the inversion symmetry and could contribute to DMI. These findings shed light on fundamental understanding and engineering of the different interfaces of magnetic garnets for advanced spintronic device applications.

Chain-of-thought (CoT) reasoning can improve problem solving, but models often keep generating after the correct answer is already reachable; the extra steps raise serving costs and may replace a correct intermediate result with an incorrect one. We propose GLOBE (Geometry-Led Online Behavioral Early Exit), an online, training-free algorithm that terminates the model's CoT process early. GLOBE embeds each completed reasoning segment as a point on a unit sphere and reads the shape of the resulting semantic trajectory. GLOBE first applies a trial phase that generates short trial answers in a separate branch, stopping the main stream on an accepted trial after checking confidence against a threshold. If generation continues, a trajectory phase stops the stream once this path repeatedly reverses direction with little net progress. On five benchmarks including mathematical reasoning, tool calling, and agent memory, GLOBE cuts output tokens by 49.7% and active end-to-end wall time (E2E) by 51.0% across two models, and achieves a five-task average of 80.58%, comparable to Full CoT.

Self-distillation policy optimization provides dense token-level supervision for LLM post-training through feedback-conditioned self-teachers. However, directly matching the self-teacher can disrupt successful behaviors on correct rollouts while providing insufficient correction on incorrect ones. We propose Asymmetric Policy Optimization via Self-Distillation (APSD), which constructs correctness-dependent targets by mixing student and self-teacher distributions: interpolation preserves successful behaviors on correct rollouts, while extrapolation beyond the self-teacher strengthens correction on incorrect ones. We analyze APSD through divergence decomposition, reverse-KL barycentric geometry, and gradient analysis, highlighting the importance of gradient flow through student-dependent targets. Experiments under reinforcement learning with verifiable rewards and rich feedback show that APSD achieves strong overall performance against reinforcement-learning and self-distillation baselines and matches SDPO performance with 2.6x fewer training steps on average across Qwen3 model scales.

Time-interleaved analog-to-digital converters (TI-ADCs) enable multi-gigasample-per-second throughput in high-speed applications, but sub-picosecond timing skews among interleaved channels introduce large spectral artifacts that degrade dynamic performance. To continuously track parametric drifts without interrupting normal operation, background calibration is required. However, extracting timing skews under unknown inputs is challenging, and many existing correlation-based methods rely on resource-heavy derivative filters that restrict input bandwidth. This article proposes a novel background timing-skew estimation technique for two-channel TI-ADCs that overcomes these limitations. Closed-form timing-skew expressions are derived using: (a) adjacent-channel cross-correlation combined with single-channel auto-correlation for sinusoidal inputs, and (b) adjacent-channel cross-correlation for Wide-Sense Stationary (WSS) inputs, specifically bandpass-filtered wideband noise and Orthogonal Frequency Division Multiplexed (OFDM) signals. The derived analytical models are validated through comprehensive simulations, offering an efficient framework for real-time background calibration in high-speed data converters.

Automated identification of diatoms from microscopic images is a cornerstone of large-scale freshwater biomonitoring, yet the high diversity of species and strong class imbalance pose significant challenges for reliable classification. In this study, we develop a ResNet-18 baseline for a 759-class diatom dataset and investigate how calibrated confidence estimates support selective classification to reduce expert workload without sacrificing taxonomic integrity. While the initial model exhibits overconfidence with an Expected Calibration Error (ECE) of 0.117, post-hoc temperature scaling (T = 2.12) dramatically improves reliability, lowering the ECE to 0.055.By leveraging these calibrated probabilities within a triage framework, we demonstrate that a Selective Macro-F1 score of 99.01% can be maintained at 66.2% coverage (rejection threshold $τ$ = 0.934). Qualitative analysis reveals that the system effectively functions as an intelligent filter, consistently deferring rare taxa-such as AAMB and AASI-and ambiguous morphologies for expert review. Our findings, supported by the torch-uncertainty framework, highlight the potential of simple calibration techniques to make automated diatom identification practical and robust, prioritizing the preservation of rare species metrics essential for ecological assessment. To support reproducibility, our code, environment specifications, and calibration results are available anonymously at https://anonymous.4open. science/r/greenprwksp-B53D/README.

Multi-hop question answering (QA) requires models to chain intermediate conclusions while remaining cost-aware. Existing training-free self-reflective protocols (generate -> critique -> revise) improve accuracy but operate on a flat token stream: revisions cannot identify which prior step is unreliable, and early stopping cannot exploit structural convergence. We introduce GraphEvoResearcher, a training-free protocol that lifts EvoResearcher's self-reflective meta-reward onto an explicit reasoning graph - nodes are intermediate conclusions/evidence and edges encode support, contradict, and depends_on. A graph-aware meta-reward combines correctness, efficiency, reflection, diversity, and four structural signals (connectivity, acyclicity, branch coverage, path convergence) to decide whether to revise, backtrack, or stop. A graph-convergence early-stop terminates when evidence branches converge on a single conclusion. On a real LLM (DeepSeek), over GSM8K, MATH, and BBH (n=50 each), GraphEvoResearcher reaches 98%, 92%, and 82% respectively, the highest of all baselines, with the largest gains on the hardest set (MATH: +24 pp over single-shot, +12 pp over flat reflection), while keeping construction cost bounded at ~2 steps / 4.5-5 nodes. Our results indicate the structural signal of a reasoning graph is most valuable exactly where single-step reasoning is unreliable.

Recent advances in deep joint source-channel coding (DeepJSCC) have shown strong robustness to channel variations in wireless image transmission. However, its integration with orthogonal frequency-division multiplexing (OFDM) typically relies on fixed pilot patterns that are not optimized for receiver- side channel processing. This work introduces Pilot-Efficient DeepJSCC-OFDM (PE-JSCC), which learns pilot placement under a strictly fixed number of pilot symbols via a Gumbel- Top-k-based selector. The learned pilot placement improves end- to-end performance over the conventional Block-JSCC, Comb- JSCC, and Scatter-JSCC baselines. To support high mobility, the receiver incorporates a lightweight axial-attention-based inter- carrier interference (ICI) canceler and a CNN-based channel estimator. Simulation results show that PE-JSCC consistently outperforms fixed pilot patterns across diverse SNRs and remains robust over a wide mobility range.

Long-horizon search requires agents to acquire relevant evidence and integrate it into an evolving research state. Existing methods maintain research states to guide exploration or assign turn-level progress signals, yet grounding these signals in explicit, attributable state changes remains underexplored. We introduce ClueFlow, which learns long-horizon search from attributed research-state transitions. ClueFlow constructs Source-State-Final attribution chains that connect evidence-acquiring browser actions, Evidence and Candidate updates, and the final answer supported by those updates. During search, ClueFlow records typed state changes and potentially supporting browser actions, then applies gold-conditioned semantic validation and source tracing after execution. We use this attribution to guide both supervised fine-tuning and reinforcement learning. During SFT, attribution selects which decisions receive supervision with their original interaction contexts. During Turn-PPO, the same attribution augments outcome-based turn advantages with credit assigned along the Source-State-Final chains. Transition-level validation also recovers useful supervision from gold-consistent state changes in trajectories with incorrect final answers. We evaluate ClueFlow across two Qwen backbones and four search benchmarks spanning live-web and fixed-corpus settings, observing consistent gains from SFT and further improvements from PPO. With Qwen3.5-35B-A3B, ClueFlow achieves 60.0% accuracy on BrowseComp and 72.0% on BrowseComp-Plus. In controlled BrowseComp-Plus experiments, attribution-guided SFT matches all-turn exact-context SFT using about 30% of the training tokens, while attribution-guided PPO outperforms outcome-only PPO by 4.1 pp. These results demonstrate that state-transition attribution enables efficient supervision and effective credit assignment for long-horizon search agents.

Integrating force awareness into Vision-Language-Action (VLA) models involves not merely encoding wrench measurements as an additional modality, but determining when and how strongly physical interaction should influence robot action generation. Existing VLAs that use force typically inject it through a fixed pathway, without explicitly determining when it is relevant to the current action. This calls for an intermediate force relevance mechanism inside the VLA, in which visual-language context estimates the relevance of physical feedback to the current task before force enters the action pathway. FR-VLA addresses this gap with a Vision-Language Force-Reasoning Model that uses learnable force query tokens to derive a force admission signal grounded in visual-language context, and uses this signal to modulate an external tokenized force pathway for action generation. In real-world experiments on five contact-rich tasks across two robotic platforms, FR-VLA achieves the highest mean success rate over six evaluated stages, and trajectory visualizations show that its force admission varies with the interaction phase.

Tool-use agents pay per decision: at each hop a language model re-reads the state and thinks for seconds, though its actions are finite and decisions recur. We present NIOCIS, a routing layer that folds execution logs into a loop-collapsed action graph (forward transitions plus recovery back-edges) answering one typed question: which declared option at a state, plus stop, does the fleet take next? A small model reads a calibrated distribution over them in one pass, emitting no text. On 1,615 production security-operations episodes we measure what the layer replaces, returns and is bounded by. Replaces: the typed encoder matches the logged next hop on 32.2% of the 3,875 held-out decisions (34.9% within the declared options) in 10 ms of encoder time (19.5 ms for the typed-choice form), against 2.2 s per LLM hop; two feature readouts reach 32.8% and 32.3%, an ordering the paired test does not resolve, so the typed layer is chosen for cost, not a separated lead. Tuning: jpt-4b reaches 9.9% zero-shot and 31.9% fine-tuned, a gap an exact paired test does not resolve (p=0.68), at 244 ms. Returns little: the realised hop falls outside the declared options for 7.9% of decisions and outside the model's top twenty for 9.3%; the most confident 15% holds 91.9% accuracy. Bounded: a cross-trace leave-one-out test puts the released state's ceiling at 25.6--44.9% as the state key grows more specific, i.e. repeated states disagree more often than they agree; the option-space ablation attributes the gain to per-node candidate restriction (+3.5 points over a flat catalog) rather than graph traversal (zero within its interval); a gated self-evolution loop lifts every arm above its anchor yet ends below full supervision; a confidence-gated cascade loses agreement when the escalation arm is the zero-shot stand-in; and agreement past a third of the fleet needs a state carrying the plan and the observation.

Learning inertial odometry for a new platform usually requires ground-truth trajectories. We show that an inertial odometry model can instead be trained from scratch by a myopic teacher that integrates the IMU over each short window independently, a scheme we call integration self-supervision. Interestingly, although supervised only by short-window velocity changes, the student learns to directly predict velocity, and does so more accurately than its integration teacher. Pose graph distillation then refines the model with sequence-consistent targets from a pose graph over many windows. Training on a new platform therefore no longer requires collecting ground-truth trajectories, but only calibrating the IMU and recording data during normal operation. Across six datasets spanning pedestrians, drones, quadrupeds, and a humanoid, the same recipe with no velocity or position labels trains models that come within 0.07~m/s average velocity error of a same-architecture supervised baseline.