arXiv:2605.00276v1 Announce Type: new Abstract: Trip planning for intelligent vehicles increasingly requires selecting optimal routes rather than merely producing feasible itineraries, as interacting factors such as travel time, energy consumption, and traffic conditions directly affect plan quality. Yet existing systems are largely designed for feasibility-oriented planning, and current benchmarks provide only reference answers without ground […]
MAEPose: Self-Supervised Spatiotemporal Learning for Human Pose Estimation on mmWave Video
arXiv:2605.00242v1 Announce Type: cross Abstract: Millimetre-wave (mmWave) radar offers a more privacy-preserving alternative to RGB-based human pose estimation. However, existing methods typically rely on pre-extracted intermediate representations such as sparse point clouds or spectrogram images, where the rich spatiotemporal information naturally present in radar video streams is discarded for model learning, while such signal processing […]
Observable Performance Does Not Fully Reflect System Organization: A Multi-Level Analysis of Gait Dynamics Under Occlusal Constraint
arXiv:2605.00778v1 Announce Type: cross Abstract: In biomechanical systems, observable performance is often used as a proxy for underlying system organization. However, this assumption implicitly presumes a correspondence between output metrics and internal system states that may not hold in adaptive systems. In this study, the vertical dimension of occlusion (VDO) is considered as a constraint […]
Remote SAMsing: From Segment Anything to Segment Everything
arXiv:2605.00256v1 Announce Type: cross Abstract: SAM2 produces high-quality zero-shot segmentation on natural images, but applying it to large remote sensing scenes exposes two problems: (1) its mask generator faces an inherent quality-coverage trade-off: strict thresholds yield precise masks but leave most of the image unsegmented, while relaxed thresholds increase coverage at the cost of mask […]
Token Arena: A Continuous Benchmark Unifying Energy and Cognition in AI Inference
arXiv:2605.00300v1 Announce Type: new Abstract: Public inference benchmarks compare AI systems at the model and provider level, but the unit at which deployment decisions are actually made is the endpoint: the (provider, model, stock-keeping-unit) tuple at which a specific quantization, decoding strategy, region, and serving stack is exposed. We introduce TokenArena, a continuous benchmark that […]
Jailbroken Frontier Models Retain Their Capabilities
arXiv:2605.00267v1 Announce Type: cross Abstract: As language model safeguards become more robust, attackers are pushed toward developing increasingly complex jailbreaks. Prior work has found that this complexity imposes a “jailbreak tax” that degrades the target model’s task performance. We show that this tax scales inversely with model capability and that the most advanced jailbreaks effectively […]
Weaving Life into Regolith: Engineered Autotrophic-Heterotrophic Consortia for Autonomous Biofabrication from Granular Feedstocks
arXiv:2406.02522v4 Announce Type: replace Abstract: Long-duration human missions to Mars will require autonomous systems capable of converting in situ resources into structural materials, tools, and functional components. More broadly, such systems represent a class of resource-limited bioprocesses relevant to extreme-environment manufacturing. Here, we investigate engineered autotrophic-heterotrophic consortia, inspired by lichen biology, as a platform for […]
REALM: An RGB and Event Aligned Latent Manifold for Cross-Modal Perception
arXiv:2605.00271v1 Announce Type: cross Abstract: Event cameras provide several unique advantages over standard frame-based sensors, including high temporal resolution, low latency, and robustness to extreme lighting. However, existing learning-based approaches for event processing are typically confined to narrow, task-specific silos and lack the ability to generalize across modalities. We address this gap with REALM, a […]
AgentFloor: How Far Up the tool use Ladder Can Small Open-Weight Models Go?
arXiv:2605.00334v1 Announce Type: new Abstract: Production agentic systems make many model calls per user request, and most of those calls are short, structured, and routine. This raises a practical routing question that existing evaluations do not directly answer: which parts of an agent workflow truly require large frontier intelligence, and which can be handled by […]
Caracal: Causal Architecture via Spectral Mixing
arXiv:2605.00292v1 Announce Type: cross Abstract: The scalability of Large Language Models to long sequences is hindered by the quadratic cost of attention and the limitations of positional encodings. To address these, we introduce Caracal, a novel architecture that replaces attention with a parameter-efficient, $mathcalO(L log L)$ Multi-Head Fourier (MHF) module. Our contributions are threefold: (1) […]
Outbidding and Outbluffing Elite Humans: Mastering Liar’s Poker via Self-Play and Reinforcement Learning
arXiv:2511.03724v3 Announce Type: replace Abstract: AI researchers have long focused on poker-like games as a testbed for environments characterized by multi-player dynamics, imperfect information, and reasoning under uncertainty. While recent breakthroughs have matched elite human play at no-limit Texas hold’em, the multi-player dynamics are subdued: most hands converge quickly with only two players engaged through […]
Beyond Structure: Revolutionising Materials Discovery via AI-Driven Synthesis Protocol-Property Relationships
arXiv:2605.00313v1 Announce Type: cross Abstract: The current structure-centric paradigm in artificial intelligence (AI)-driven materials discovery, despite delivering thousands of candidate structures, is stalling at a critical barrier: the synthesizability gap. We argue that closing this gap demands a pivot to a synthesis-first paradigm in which executable synthesis protocols, not just atomic configurations, are treated as […]