Search research

Anticipating whether a person will interact from one's own perspective is a highly intuitive task for humans, that relies on a combination of cues. We investigate how humans perform at predicting a person's intention to interact from a service robot's point of view, using pose-only or full video input, then benchmark different lightweight pose-based models and state-of-the-art vision-language models. We conducted our benchmark on the HUI360 dataset on a fixed pilot subset of 100 test tracks (25 positive, 75 negative). We found that with pose-only input, human annotators outperform lightweight trained pose models but not by large margins (+0.08 in F1-Score). But when given full egocentric video with a target bounding box, human annotators perform substantially better and largely outperform the Vision-Language Models (+0.2 in F1-Score). We also compared VLMs of different size and under different input conditions, and found that the best results do not correlate with model size. Our result confirms that predicting interactions is a challenging task for social robots and that reasoning-capable models are necessary but their actual reasoning capabilities alone do not suffice to match the social intuition of humans.

Local pedestrian-vehicle forecasting spans heterogeneous physical scales: pedestrians combine root locomotion with articulated motion, whereas vehicles are rigid bodies described by kinematic state and oriented extent. Existing road-agent forecasters typically omit pedestrian articulation, while pose forecasters leave vehicle futures outside the learned rollout. We introduce PV-WM, a history-only world model over structured post-perception tracks. It recurrently advances pedestrian root motion, 15-joint articulation, and learned vehicle states within a synchronized heterogeneous state. The generated pedestrian and vehicle chunks supply the next recurrent boundary; vehicle boxes are reconstructed from predicted center and heading with observed extent, and P-V geometry is recomputed after every transition. Relative to a matched one-shot complete-state predictor, recurrent execution reduces Root ADE by 12.7% and MPJPE by 14.8%. Feedback interventions show that later predictions depend on the content, temporal order, and pedestrian identity of generated articulation. Across 824 aligned Waymo contexts, with 797 providing valid future vehicle support, PV-WM reduces Root ADE by 5.2%, MPJPE by 7.6%, P-V distance error by 11.9%, and oriented-box closest-approach error by 5.8% relative to a validation-selected Modular Specialist. The single-network model uses 57.1% fewer parameters, 96.5% lower average FLOPs per local scene, and 25.5% lower measured p95 latency. PV-WM unifies this heterogeneous future state while preserving type-specific pedestrian and vehicle dynamics.

SLAM systems based on 3D Gaussian Splatting (3DGS) have recently demonstrated promising reconstruction accuracy for dense 3D scene representations. However, current 3DGS systems struggle to meet the strict demands of real-world deployments due to severe limitations in operational performance and map adaptability. To this end, we propose LightSplat, a hybrid-representation RGB-D SLAM framework. It synergizes local sparse features for robust and fast tracking with a dual-thread backend that progressively constructs dense Gaussian submaps. Crucially, we enable online loop closure through feature-accelerated 3DGS registration, refining overall map consistency through pose graph optimization. Ultimately, LightSplat achieves the online reconstruction of high-fidelity Gaussian map. Extensive experiments on multiple datasets and real-world robotic platform demonstrate that our method achieves near state-of-the-art reconstruction quality and the capability to accommodate practical camera motions, maintaining an average framerate of 8 FPS. Overall, LightSplat provides an efficient and robust foundation for deploying high-fidelity 3DGS in real-world environments.

Scaling the interaction horizon-the maximum number of environment interactions per episode-improves LLM agents on long-horizon tasks, and curriculum-based methods that progressively expand the horizon outperform fixed-horizon alternatives. However, existing schedules are open-loop: they monotonically increase the horizon until a manually specified maximum, with no mechanism to detect when further expansion stops helping. We propose the effective interaction frontier hypothesis: a dynamic boundary beyond which additional interactions yield diminishing returns while cost grows linearly. We then introduce Elastic Horizon, a closed-loop controller that tracks this boundary via the 90th percentile of successful trajectory lengths. On AppWorld and BFCL, fixed-horizon sweeps reveal clear saturation plateaus; Elastic Horizon stabilizes the horizon inside the saturation band from both under- and over-capacity initializations, attains the best success rates across 7B and 14B backbones, and saves up to 25% of per-step trajectory tokens. Our work shifts the paradigm from how to scale interaction horizons to when to stop scaling.

Selecting a parallelism strategy - the configuration of data, tensor, and pipeline parallelism degrees together with micro- and global-batch sizes - largely determines the training efficiency of large language models. State-of-the-art methods search for a parallelism strategy offline and select the single strategy that minimizes per-iteration time. But we find that they neglect the target validation perplexity and time-to-perplexity (TTP). In particular, our analysis reveals that the best strategy yielding the fastest perplexity improvement changes multiple times during training. As a result, state-of-the-art methods are 1.8-11.4x slower in TTP than the strategy sequence that selects the best strategy at each iteration. This paper proposes CONA, a new training method that introduces online strategy chaining. Instead of a single strategy selected offline, CONA ranks candidate strategies during training using a surrogate metric built from compute throughput and gradient statistics, and switches the current strategy to a new strategy with a higher metric. In our evaluation with GPT-3 1.3B, BERT-Large, and Llama-3.2-1B, CONA reaches the target validation perplexity 1.4-9.6x faster than state-of-the-art methods. Moreover, CONA closely tracks the perplexity achieved by the sequence that selects the best strategy at each iteration, within 2.6%.

Several properties safety monitors are asked to certify, among them cross-tenant noninterference, sandbagging and evaluation awareness, are 2-safety hyperproperties, witnessed only by two executions. The standard consequence is a binary impossibility: one trace cannot decide them. We replace the binary with a measurement. A tight bound puts the balanced accuracy of any single-trace monitor at $\tfrac12+\tfrac12\,TV(P_0,P_1)$, turning undecidability into a graded detectability frontier and defining an oversight gap: a monitor's shortfall below it. On a leak family with closed-form $TV$, nine LLM monitors are optimal at $TV=0$ but capture little signal as $TV$ grows; at $TV=1$, where a 20-line membership check scores $100\%$, they average $60.9\%$. That shortfall is mostly not capability: naming what to check closes $61\%$ of it while leaving the $TV=0$ control at chance. The same split runs through a $2{\times}2$ factorial: an imagined second run leaves monitors at chance ($50.4\%$) while the same rule on an executed second run reaches $90.0\%$, and a stored oracle without a comparison procedure yields only $68.2\%$. Information and procedure are each necessary and neither is capability. Under nondeterminism, replay tracks a closed-form $k$-replay curve only under the right projection, and a projection frontier shows the resulting dilemma is forced: narrow misses $98.6\%$ of off-channel leaks, broad flags $75.7\%$ of clean traffic, and attainable accuracy decays like $1/(qm)$ in the benign-variation rate and the channel count. Finally, two frontier LLM judges certified an earlier version of our own benchmark as sound while a sign test found a directional bias ($p=2.7\times10^{-5}$) that invalidated three of our findings. Construction validity for hyperproperty benchmarks should be proved mechanically, not audited by models.

This paper presents our system for CCL2026-Eval Task 5: Minor-Grain Breeding Information Extraction (MGBIE), which jointly extracts 12 entity types and 6 relation types from minor-grain breeding literature. We propose RAME (Retrieval-Augmented Multi-Prompt Ensemble), a training-free framework that elicits multiple LLM outputs under controlled diversity and aggregates them by majority voting to obtain high-confidence predictions. RAME combines (i) retrieval-augmented few-shot selection via a hybrid BM25-embedding retriever, (ii) a three-prompt ensemble (Strict, Relaxed, Balanced) spanning the precision to recall spectrum, and (iii) large-scale repeated sampling with majority voting to filter noisy predictions. Built on DeepSeek-V4-Flash, RAME achieves a Total Score of 0.499 (NER 0.730, RE 0.346) on the leaderboard, ranking 1st and surpassing the official Track-A baseline powered by GPT-5.5 (0.448), representing an 11.4% relative improvement. Code is available at https://github.com/king-wang123/CCL26-RAME.

In world model planning, sensing inputs pass through an encoder and predictor before affecting planner decisions, so final task success alone cannot reveal where sensing disturbances attenuate or persist in the pipeline. We apply 10 visual and temporal sensing degradations to a world model planner and track their effects across representation, future prediction, planner preference, and physical outcome using paired evaluation on the same 50 tasks. The relative impact of degradations was not preserved across stages: large representation shifts could attenuate downstream, while smaller initial shifts could persist to the outcome, and internal-response ordering did not directly match physical-outcome ordering. Temporal degradations also showed distinct patterns: even with similar overall changes in observation history, responses differed substantially with the location of corrupted information and the planner's actual exposure. This non-uniform stage-wise response was also observed in secondary evaluations with another manipulation task and a different world model. Stage-wise diagnosis can therefore identify where sensing disturbances attenuate or persist and help prioritize subsequent model verification and sensing mitigation.

Urban air quality can vary significantly along transit corridors, necessitating high-resolution monitoring. This work introduces a novel mobile-sensing dataset from Surat, Gujarat, India, comprising PM$*{2.5}$ concentrations, meteorological variables (temperature, humidity, wind speed, wind direction), and land-use features. To represent the spatiotemporal data as a graph, two node-definition strategies were used: (i) uniform segmentation (200--400~m intervals) and (ii) DBSCAN clustering to adaptively group dense observations. For each node, rolling mean and standard deviation of meteorological variables were computed. To model this high-dimensional data, we propose a SA-GNN for fine-grained, short-term PM$*{2.5}$ forecasting and hotspot identification. We compared SA-GNN with LSTM, RNN, GRU, and ANN models. These models performed well on low-resolution data but had difficulty capturing rapidly changing patterns in urban air quality. SA-GNN employs cluster-specific GRUs to capture localized temporal dependencies and a Graph Attention Network to learn spatial heterogeneity. This hybrid architecture effectively models rapid fluctuations and complex spatial interactions. On our dataset, SA-GNN achieved $R^2 = 0.95$, RMSE $= 6.8$, and MAE $= 4.2~\si{\micro\gram\per\meter\cubed}$, outperforming all baseline models. Combining spatial clustering with adaptive attention significantly improves forecasting, enabling real-time, fine-grained monitoring and supporting personalized exposure tracking and timely alerts for healthier cities.

Federated learning enables distributed training without requiring clients to share their raw data. However, its reliance on the integrity of the client-submitted updates exposes the global model to stealthy backdoor poisoning. Existing defenses often rely on individual evidence sources, but stealth-constrained attacks can adapt to these signals. Such attacks can suppress anomaly signals they are optimized to evade, yet their poisoned updates still leave residual structural traces. We propose FedMAST, a Federated Multi-Axis Structural Tracing defense for backdoor detection in federated learning. FedMAST scores client updates using complementary structural, spectral, and historical evidence and then applies tiered filtering and round-level containment to limit adversarial influence. To capture traces that isolated signals may miss, FedMAST uses squeeze-pair coherence scoring to expose coupled feature distortions and signed spectral-drift tracking to reveal persistent directional changes over time. Across six backdoor attacks, FedMAST achieves lower attack success rate (ASR) than baseline defenses in all nine evaluated comparisons, averaging 1.51% ASR and 94.84% main-task accuracy (MTA) across the complete 200-round runs. Over the full 200-round method-aware CovertLayers run, FedMAST achieves 1.53% ASR and 92.26% MTA, compared with ASRs of 100.00%, 99.67%, 99.53%, and 32.84% for FedAvg, MultiKrum, AlignIns, and FLAME, respectively.

Performance modeling is central to hardware design and software optimization, yet constructing these models requires structured reasoning about computation, data reuse, storage, and movement. We introduce PerfReasoning, a benchmark that evaluates LLMs both as direct performance reasoners and as generators of analytical performance-model code. Given workload, architecture, and mapping specifications, models compare mappings and predict off-chip traffic and buffer requirements. The strongest closed-source models exceed 90% on reasoning-based Q&A, and the best open-weight model reaches 82.4%. However, model construction is substantially harder: while GPT-5.6 Sol exceeds 80% pass rate, all other model configurations average below 45% and vary markedly across runs. Task-specific RL raises a 4B model's mapping-reasoning accuracy by 15.7 points, whereas feedback-free multi-round self-revision prompting is not reliably effective. PerfReasoning exposes the gap between plausible architectural reasoning and reliable performance-model construction. We will publicly release the benchmark to support reproducible evaluation and track future progress.

Language-model judges now gate training data, score generations, and drive leaderboards. The judge is then a measurement instrument, resting on one rarely stated assumption: the same request, sent to the same model name, reads the same tomorrow. We audited that assumption in two preregistered campaigns with every threshold fixed in advance; neither got past validating its instrument. Across 52,988 audited request attempts, same-window repeat rankings agreed at Spearman 0.400 against a required 0.90, and byte-identical next-day replays agreed at 0.78 against a required 0.99, each time with the execution record at ceiling. Three mechanisms explain the gap: a label-to-meaning mapping that biased readouts as strongly as the signal; candidate gaps seven orders of magnitude below the instrument's own noise floor; and byte-identical inputs returning different rankings, a noise that exact-permutation readouts compound. Neither metric substitution nor sampling repaired it on the tested grid. Preregistered follow-ups bound the problem: waiting did not help on the days sampled (0.805 versus 0.800, replicated over five further days); switching providers did not help (four providers share the floor, medians 0.74 to 0.88, predicted by none of the metadata fields they expose); self-hosting on batch-invariant kernels helped only while the server was quiet; and on constructed errors with known gaps, the readout's separation tracks error type, not size. We distill the evidence into a three-level snapshot-identity ladder, eight design rules, and a reporting checklist; a pilot at roughly 2% of the study's call volume would have exposed both unreachable gates in advance. All results concern externally measured behaviour on shared serving infrastructure. On a shared endpoint, a model name is not a frozen instrument; a preregistered evaluation must measure its instrument before freezing any gate on it.

Cortical neurons fire sparsely -- often fewer than one spike per sensory window -- making rate coding insufficient and temporal coding a necessity. That conduction delays convert firing order into synchrony is long established. What governs which class of temporal feature a neuron detects -- one volley of coincident input, or two in a particular order -- has not been examined. We propose a delay-signature framework in which the axonal conduction delays converging on a dendritic branch constitute a physical key: only input sequences whose spike-time differences the delays compensate arrive synchronously, and coincidence detection, via calcium plateau thresholds, converts that synchrony into an all-or-none output. In simulations of an integrator-neuron model we report three results. First, a single physical scalar -- the dispersion of the delay set -- moves a population from event detection to order-selective sequence detection. The transition is emergent under random delays and connectivity: at narrow dispersion sequence detectors do not exist, and the dispersion at which they overtake event detectors tracks the inter-event interval with a slope statistically indistinguishable from one. This maps a computational distinction onto the anatomical one between myelinated and unmyelinated projections, making myelination a switch on what a neuron computes, not only a regulator of speed. Second, the same dispersion sets the code's limits: it bounds the longest codable interval and fixes an absolute timing tolerance of about a millisecond, with slowing better tolerated than speeding. Third, that millisecond window and horizontal conduction velocity together predict cortical column diameter, and the two areas with direct measurements fall where the relation puts them. One anatomically measurable parameter thus sets what a neuron detects and the limits of what it can represent.

For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that inform us about failure cases. As models get stronger, standard benchmarks for machine translation are approaching saturation. Further, automatic translation metrics are unreliable, vulnerable to reward-hacking, and provide unactionable assessments. Even gold human evaluation is not problem-free, because it often lacks reproducibility, objectivity, and scalability. Overall, this prevents us from tracking objective progress in the field and identifying pathways for improvement. We introduce the Last Translation Benchmark, a collection of human-authored and peer-reviewed examples (texts, images, audio, videos) that break leading machine translation models. We also present a new evaluation approach: each example comes with handcrafted verification rules describing concrete failure cases on that example, therefore allowing reliable and actionable future evaluation. The Last Translation Benchmark is a live dataset that accepts ongoing contributions. The latest version is LTBv1, containing accepted contributions prior to September 1st 2026, with future releases planned as new data is continuously collected.

Reinforcement Learning from Verifiable Rewards works well when a task has a programmatic checker, but most long-horizon agent domains have none. We work in the outcome-blind setting, where ground-truth success signals are not available. Multi-criteria rubrics are a popular way to supply such a reward; they are scored once per trajectory, but a single scalar is a poor signal across tens of steps. We propose DRACO: Distributing Rubric-based Advantage for Credit Optimization. It generates rubrics dynamically during training to track the policy's evolving capability, scores those rubrics once per completed trajectory, and redistributes that judgment over the steps responsible for annotated rubrics to produce differentiated per-step advantages in GRPO. The redistribution is closed-form and does not introduce any trained attribution module. On AppWorld, DRACO gains 15.9 points over the base model and 5.3 points over GRPO trained with a sparse ground-truth reward, despite not using any verifiers itself. On out-of-domain Tau-Bench, it gains 5.3 points over the base model even without a frontier judge, beating both ground-truth-reward training and other rubric-based training settings. The code for DRACO is available at https://github.com/IBM/draco.

Reinforcement learning from human feedback (RLHF) has emerged as a powerful yet sample-inefficient approach for learning reward models from human preferences, making active learning a critical component in synthesizing informative preference queries. However, effective uncertainty quantification required for active learning remains a key challenge for large neural network reward models. In this paper, we introduce PreferenceEKF, a sample-efficient approach that tracks reward model uncertainty by framing active preference learning as a sequential Bayesian filtering problem. Instead of relying on computationally prohibitive posterior inference over the full neural network parameter space, our method performs sequential inference via an extended Kalman filter within a low-dimensional parameter subspace, continuously updating the reward model posterior as new preference queries arrive. Our approach enables scalable sampling of neural network parameters to efficiently compute acquisition functions for active reward learning. Experiments on the D4RL and V-D4RL benchmarks demonstrate that our approach achieves better sample efficiency, runtime, scalability, and calibration compared to other Bayesian deep learning approaches, and the learned reward models lead to competitive offline reinforcement learning policy performance. This highlights the potential of scalable Bayesian methods for preference-based reward modeling in RLHF. Our code is available at https://github.com/yutaizhou/bnn_pref.

In online meeting delegation, LLM agents fail to recognize when to speak. With no structured way to track stances, coverage, and floor, they miss the moments where they should contribute. Prompt-only delegates stay silent on 51.4% of the absent participant's talking opportunities on the AMI corpus. We present CAPA (Collaborative Agent Predictive Architecture), an architecture for online meeting delegation. A Perceiver updates the meeting state from each observed turn. A Predictor forecasts how the conversation will continue. A Controller decides whether to speak and which proposition to surface. A Generator phrases the chosen contribution in the participant's style. Two judges score the forecast and the action against the next observed turn. A Recalibrator updates the meeting state from those verdicts for future decisions. To evaluate online delegation, we introduce an episode-level protocol that scores whether, when, and what a delegate contributes around the participant's actual idea units. The protocol's schema-constrained LLM judges align with human annotations at Cohen's kappa = 0.71. On 137 AMI meetings, CAPA reduces the silence rate from 51.4% to 2.5%, doubles credited recovery (26.1 --> 52.2), and keeps hallucination at 0.6%. The failure mode shifts from omission to selection, with each residual near-miss attributable to a specific module of the architecture. Mechanism ablations identify the meeting state as the lever that closes the recognition gap, where raw-context scaling alone does not.

Semantic mapping plays a crucial role in the ability of a robot to interact with objects, operate and navigate a complex environment. The most common pipeline for semantic mapping consists of geometric mapping and localization (SLAM), perception, semantic fusion and semantic representation. However, more recent works also integrate a form of prior knowledge in their application, most notably knowledge graphs or semantic scene graphs, to improve contextual understanding of the environment. In this paper, we present a hybrid pipeline for semantic mapping. Our system incorporates an external calibrated camera using homography projection for geometric mapping and localization, combined with object detection, persistent object tracking and ontology driven semantic updates to build a dynamic semantic world model. Linear regression models are also used for correction of the estimated values of real world coordinates. The system continuously updates object instances, spatial properties and semantic relations based on real time sensory data. Ontologies are selected as form of knowledge representation due to their hierarchical structure, semantic expressiveness and support for dynamic world modelling.

Large language model agents have shown promise in bioinformatics, but most existing systems focus primarily on producing final answers, treating planning, tool use, and code execution as transient interactions. This design is poorly suited to long-horizon bioinformatics tasks, where conclusions must remain connected to the data, computations, and intermediate evidence that support them. We introduce \textbf{Bioinfoysis}, a multi-agent harness that represents each request as a persistent, artifact-grounded analysis run. Bioinfoysis combines global planning with step-wise, evidence-driven replanning: the planner maintains an executable checklist and revises pending steps using structured handoffs returned after each worker execution. These handoffs bind intermediate results to their responsible agent, checklist step, and plan generation, preventing stale evidence from being silently reused after replanning. A controlled runtime validates generated scripts, tables, and figures before they are used in downstream analysis or reporting, while role-specific context, persistent memory, and governed bioinformatics skills support reliable execution over long analysis trajectories. We evaluate Bioinfoysis on BixBench and two question-answering tracks of LAB-Bench 2. On BixBench, Bioinfoysis achieves state-of-the-art accuracy of 82.4%. Across four underlying language models, Bioinfoysis increases average accuracy from 27.81% to 64.13% on SeqQA2 and from 3.13% to 31.25% on DbQA2. These results demonstrate that reliable bioinformatics automation depends not only on model capability, but also on the harness that governs planning, execution, memory, and evidence flow. We hope that the emergence of Bioinfoysis will play a driving and leading role in the development of the bioinformatics community. Our demo website can be seen in https://report.bioinfoysis.com/.

Background. Remote photoplethysmography estimates the cardiovascular pulse from facial video, and its explanations have rested on inspecting heatmaps rather than on quantitative evidence about where a model reads it. We quantified the explanations and asked whether such explanations transfer between datasets and track model performance. Method. We trained eight condition-specific RhythmFormer models on NCKU-rPPG, recorded under three illumination levels, speaking, rotation, and cycling, estimated one heart rate per 5.12-second clip, and set them beside a UBFC-rPPG reproduction. Raw attention, rollout, attention flow, and Beyond Intuition were assessed by skin coverage and the Salience-guided Faithfulness Coefficient (SaCo). Results. Beyond Intuition ranked highest on both datasets, at median coverage 0.789 and SaCo 0.837 on Static level 3 against 0.826 and 0.917 on UBFC-rPPG; lower ranks differed. Within one participant of one condition, neither measure was related to a clip's heart-rate error, waveform correlation, or signal-to-noise ratio on either dataset: 186 of the 252 coefficients fell below $|ρ|=0.10$ and 28 reached $p<0.05$ against the 13 expected by chance. Across the eight scenarios only Beyond Intuition's coverage followed the three performance measures, at $ρ=-0.43$, $+0.57$, and $+0.43$, while the attention-only methods' SaCo ran opposite to each. It failed at 40 lux alone, its median coverage falling to 0.180 and its median SaCo to $-0.178$, whereas motion degraded the estimates far more without such a drop. Conclusions. Skin coverage and SaCo carry information complementary to the performance measures rather than a proxy for them: attributing to the skin does not guarantee an accurate estimate. What an attribution reveals about a condition is where the model looks rather than how faithfully its map is ordered.

Multimodal language models achieve near-ceiling scores on food recognition benchmarks, yet it remains unclear whether this success reflects genuine cultural understanding or mere visual matching. To probe this distinction, we introduce CulturalMenuBench, a benchmark of 4,870 items in 10 languages across 18 regions; its 10 tasks pair final-dish and step-by-step cooking images with ingredients, procedural text, and regional labels, spanning basic recognition to process-grounded cultural attribution. Evaluating 12 models exposes a substantial knowledge-application gap: models exceeding 94% on standard multiple-choice tasks drop to at most 56% when attributing dishes to Chinese regional cuisines, despite an identical four-way format. Diagnostic analyses explain why: error patterns are consistent with random guessing, accuracy tracks visual distinctiveness rather than cultural structure, and models classify cuisines more accurately from dish names alone than from images (+7-18 points). The knowledge is thus present but cannot be activated through visual input. An ablation confirms these tasks genuinely require procedural evidence: removing sequential cooking images selectively degrades process-grounded tasks while others remain stable. Overall, CulturalMenuBench shows that near-perfect recognition can conceal an inability to apply cultural knowledge, motivating training that explicitly connects perception, procedure, and cultural context. Code and data are publicly available.

Developing humanoid robots capable of leveraging human behavioral data is essential for general-purpose embodiment, yet conventional development remains bottlenecked by a decoupled paradigm that isolates hardware design from whole-body control. This approach leads to suboptimal systems that compromise human-like fluidity and agility. To bridge this gap, we introduce a data-driven morphology-control co-design framework that optimizes humanoid morphology for human-like movement. To quantify morphological fidelity, we also introduce a novel metric that jointly considers kinematic retargeting fidelity to human motion and dynamic tracking performance. Our framework achieves state-of-the-art (SOTA) performance across all metrics compared to baseline humanoids (Bumi, K1, and Toddlerbot). Finally, we realize this design in Bridge, an open-source, 88cm-tall humanoid platform released alongside its control policy. We demonstrate that Bridge captures human motion data with superior fidelity, exhibiting exceptional performance across foundational locomotion, robust balance, and highly dynamic maneuvers. Videos and open-source materials: https://sites.google.com/view/bridgerobot.

Camera traps have become an essential tool for wildlife monitoring, motivating the development of computer vision methods for the automated extraction of information from these data. While most prior work has focused on species identification, many ecological applications also require estimating the number of unique individuals appearing across short image sequences. This task is particularly challenging because camera traps typically acquire bursts of images at approximately one frame per second, creating large temporal discontinuities that may make conventional multi-object tracking methods unreliable, and because manually collecting individual count annotations is prohibitively expensive. In this work, we describe the winning solution to the iWildCam 2021 Challenge, which introduced a benchmark for counting animals at the sequence level under realistic annotation constraints where count annotations are unavailable for training. Our approach, MaxBoxCount, combines a strong species classification pipeline with a simple yet effective counting heuristic based on MegaDetector detections to estimate the number of unique individuals without requiring count annotations. Code is available at https://github.com/alcunha/iwildcam2021ufam.

Multi-segment soft robotic arms can continuously reconfigure their body shapes for safe interaction, but tip control alone is insufficient for constrained-space tasks. Therefore, shape control is a more important task for multi-segment soft arms than tip control, but remains challenging due to the high dimensionality and nonlinear dynamics of continuum deformation. In existing work, shape control accuracy is defined by the error in the global frame (global shape error). For multi-segment soft arms, using only global shape error as the control objective is insufficient, as segment coupling, gravity-induced loading, and inertial effects become more significant. This difficulty increases with the number of segments. In this paper, we present a Koopman-based model predictive control framework that combines global and local observables, enabling real-time shape control on multi-segment soft robotic arms. The framework is evaluated through numerical and physical experiments. Numerical experiments demonstrate the scalability of the proposed controller by achieving shape control on robots with up to 10 independently actuated segments. The physical experiments demonstrate that the controller is capable of (1) real-time shape control of 3- and 5-segment robotic arms with tip speeds up to 0.6 m/s, (2) robust tracking without retraining, including distal payloads up to 400g and recovery from a 7N lateral disturbance, and (3) the potential for future inspection applications through a confined-space demonstration. These results demonstrate that the proposed framework enables dynamic, scalable, and accurate real-time shape control on multi-segment soft robotic arms.

Continuous chain-of-thought models compress reasoning into latent tokens. Matrix-valued variants, which route each latent token through a d x d matrix bottleneck, introduce rank as a single-sample structural observable on the latent matrix Z. If matrix latents carry parallel reasoning paths via superposition, rank should track them, and truncating Z to low rank should hurt accuracy on tasks whose solutions plausibly require multiple components. Across four training regimes of a matrix-CODI model (three on ProsQA, one on GSM8K-Aug below the learning threshold), the rank-k projection ablation curve is flat to within 0.6 percentage points. A three-seed replication yields 81.0 +/- 2.0 percentage points accuracy while the final effective rank of Z spans {4, 12, 13}; the loss does not reward any particular rank. To test whether rank-blindness arises from the flatten-then-project readout alone, we trained four readouts: a bilinear reparametrization, a bilinear-plus-GELU readout nonlinear in Z, an SVD-augmented readout feeding singular values through an MLP, and a quadratic readout in Z Z^T. All four rank-k curves remain flat (Spearman p-values 0.63, 0.14, 0.82, 0.46). The flat curves persist for readouts nonlinear in Z. A linear probe on Z underperforms a raw pretrained hidden state at target prediction (AUC 0.673 vs. 0.846). A negative control on vanilla GPT-2 SFT (no matrix bottleneck, no Z, three seeds, n=500) reproduces a flat rank-k curve under the same intervention paradigm with pooled-mean range 0.20pp, and a random-h sensitivity floor lands at the same accuracy: the rank-k ablation alone conflates rank-blindness with position-irrelevance.

Sign language processing systems have traditionally operated at the sentence level, ignoring critical discourse phenomena fundamental to sign language comprehension. We introduce DiscoSign, a computational approach for discourse-aware text to sign language gloss translation grounded in linguistic research. We address three key phenomena within our modular Large Language Model (LLM)-based translation framework: (i) spatial coreference resolution, where entities maintain consistent spatial locations throughout discourse; (ii) Question-Answer Clauses (QACs), pseudocleft structures serving specific discourse functions; and (iii) concept-gloss consistency, ensuring stable mappings between English concepts and American Sign Language (ASL) signs. Traditional translation metrics fail to capture discourse-level quality, so we introduce a suite of novel evaluation metrics designed to assess each dimension of discourse coherence addressed by our framework. Experiments on sentence-level and discourse-level datasets show that our approach for discourse-aware processing significantly improves spatial consistency and entity tracking relative to sentence-only translation, while maintaining competitive single-sentence gloss translation quality. Our work establishes the first systematic framework for discourse-level text to sign language gloss translation with corresponding evaluation methodology.

Leech-lattice vector quantization holds the strongest reported 2-bit quality under its own evaluation protocol. Its kernel decodes one shell; we found no implementation of the multi-shell decoder the rate requires. This paper supplies one and measures its serving cost for decode-phase GEMV at batch 1. First, a serving path for the full 301-class codebook: an offline expansion into GPU layouts and a fused dequantize-plus-matvec kernel reading them without warp divergence, verified against f64. Second, the in-VRAM rate is a design axis distinct from the on-disk rate. Four bit-exact layouts timed in one process show binary bit planes beating one-hot masks on size and speed at constant bandwidth (4.80 bits per weight, 2.15x FP16). Below 4.3 bits a second, irregular stream enters; at 3.6 the decode stops being shifts and masks. Third, deployed four-bit (AWQ) and two-bit (QTIP) GEMV kernels run in the same process. The trellis kernel reads 2.40x fewer bytes than our served layout and runs 2.27x faster at near-equal fractions of their byte bounds: the time gap tracks the traffic gap, the price of unfolding a codebook too large for a lookup table. Fourth, the validity envelope: the trellis kernel outruns our no-weights control, so our launch geometry sets that floor, and on a second memory hierarchy every lattice arm falls below FP16. With the output head held identical across arms, the kernel-and-format path gains 1.11x, 1.29x and 1.41x end to end at 4B, 8B and 14B; with an int8 output head the served 4B reaches 87.0 tok/s in 2.60 GB. The quality cost, 1.38x perplexity and 14.7 MMLU points at 4B, shrinks across the three sizes measured.

Current evaluations and training of multimodal models predominantly focus on multi-image tasks, largely overlooking interleaved text-image scenarios. In such multi-image tasks, text typically serves merely as task instructions, lacking deep semantic interaction with the visual content. In contrast, realworld applications like text-image co-creation, character tracking, and spatial reconstruction require constant interaction between text and images. Consequently, models must possess a deep understanding of these interleaved contexts. To bridge this gap, we introduce a novel benchmark, TIC-Bench (deeply interleaved Text-Image Contexts), designed to evaluate the capability of models to integrate text-image clues and recover the ground truth facts within deeply interleaved contexts. This benchmark encompasses three core domains: Logical, Temporal, and Spatial Association, which are further categorized into eight specific types, comprising a total of 2,280 questions. We evaluated 10 state-of-the-art MLLMs and observed a substantial performance gap compared to human experts, together with persistent difficulties in integrating evidence distributed across interleaved visual and textual inputs. Ultimately, this benchmark provides a valuable analytical tool for assessing and advancing the ability of multimodal models to effectively integrate text and image information in deeply interleaved contexts. TIC-Bench is publicly available at https://huggingface.co/datasets/pino10010/TIC-Bench

Beauty assessments from Multimodal Large Language Models (MLLMs) are increasingly popular amongst users, companies, and aestheticians. This raises the question of whether these AI models can accurately reflect human judgments of attractiveness. In a pre- registered exploratory study, we compared the attractiveness ratings of 2,513 human participants to four widely used commercial AI models: Claude, Gemini, GPT, and Grok. Results showed that MLLMs systematically rate faces more favourably and within a narrower range than humans and, at the time of study, do not reproduce human ratings in absolute terms. However, MLLMs exhibit strong correlations with human attractiveness judgments, accurately tracking the rank-ordering of faces. MLLMs may judge faces by different cues than humans; only face age was a predictor of facial attractiveness in both humans and MLLMs, with inconsistent patterns across models for ethnicity and gender. AI models strongly agree with one another, except for Grok, which also showed the lowest agreement with humans. Our findings suggest that while they may be able to approximate rank-orderings of human attractiveness, current off-the-shelf commercial MLLMs systematically overrate the beauty of human faces.

Safety alignment trains large language models to refuse harmful requests stated plainly, but that training is applied mostly to surface form. Requests that only recontextualise the same operational content, changing how the model reads it, are therefore only weakly covered. The ASCII Attack is one such recontextualisation. It is single-turn and black-box: one message, with no access to model internals. It embeds a fully legible harmful request in ASCIl-art characters, presents it as artwork, and asks for feedback. Unlike ArtPrompt, it hides nothing: the request stays readable. The reply is written as artistic critique and can contain operational detail that a plain request would have been refused for. Every framed prompt is paired with a direct-question control, so the contrast is isolated from topic, model and decoding variation. The contrast identifies a bundled surface, not one isolated channel. Across eleven models and eight harm topics, a harm-aware classifier judges 62% of framed prompts harmful against 42% of controls. On the most susceptible model the framed prompt succeeds 93% of the time. A single query matches or exceeds published single-query attacks under four of five harm judges. The effect tracks the model more than the topic and does not diminish with scale. At least one judge dissents from the panel majority on nearly two-thirds of framed rows, which is itself a measurement-validity finding. That pattern is consistent with mismatched generalisation.