Knowledge catalogue
arXiv:2609.37171v1 Announce Type: new Abstract: Retrieval-Augmented Generation has established itself as a fundamental framework in natural language processing, seamlessly integrating information retr
arXiv:2609.37012v1 Announce Type: new Abstract: For a long-horizon agent, context is the bottleneck: the history is resent with every request, the window caps task length, and reasoning degrades as th
arXiv:2609.36828v1 Announce Type: new Abstract: Post-training quantization (PTQ) lowers deployment cost for multimodal large language models, but calibration typically reconstructs fixed sequences wit
arXiv:2609.36331v1 Announce Type: cross Abstract: The state-of-the-art Membership Inference (MI) methods calibrate their signal separately for each example using reference models, auxiliary models tra
arXiv:2609.35795v1 Announce Type: cross Abstract: Asthma deterioration forecasting must remain reli- able when patient populations, sensor ecosystems, and available modalities change across cohorts. E
arXiv:2609.36726v1 Announce Type: new Abstract: Can a scientific agent distinguish a law it inferred from evidence from one it merely recognizes? We introduce Synthetic Universes, a controlled benchma
arXiv:2609.37837v1 Announce Type: new Abstract: Vision-Language Models (VLMs) remain vulnerable to cross-modal implicit risks: visual and textual inputs that appear benign in isolation can jointly eli
arXiv:2609.35821v1 Announce Type: new Abstract: Disaster social sensing converts public social-media posts into evidence for situational awareness and humanitarian needs, but generative artificial int
arXiv:2609.36776v1 Announce Type: new Abstract: Emotional Video Captioning aims to generate factually accurate and emotionally empathetic descriptions. While recent methods have recognized the importa
arXiv:2609.35909v1 Announce Type: cross Abstract: Autonomous LLM agents turn vulnerability discovery into a repository-scale search: they generate many vulnerability hypotheses but can verify only a s
arXiv:2609.36308v1 Announce Type: new Abstract: Reinforcement learning has helped AI agents solve increasingly difficult tasks, but high rewards do not always reflect the work users intended. In recen
arXiv:2609.36965v1 Announce Type: new Abstract: System One models such as Jev offer an efficient alternative to generative language models for tasks that require decisions rather than open-ended respo
arXiv:2609.38136v1 Announce Type: new Abstract: Style transfer aims to render target content in the style of a reference image, but existing methods often suffer from content leakage, where objects, l
arXiv:2609.36495v1 Announce Type: new Abstract: Forward kinetostatics of spatial tendon-driven continuum robots typically requires a nonlinear equilibrium solve for each actuation input. This paper de
arXiv:2609.37875v1 Announce Type: new Abstract: Inverse design of physical systems (molecules, devices, microstructures) often reduces to optimizing a high-dimensional structure against an expensive b
arXiv:2609.36024v1 Announce Type: new Abstract: Reconstructing simulation-ready 3D scenes from real-world observations enables robotics, gaming, and immersive applications, yet existing methods largel
arXiv:2609.36935v1 Announce Type: new Abstract: Long-context reasoning is essential for complex and long-horizon tasks, yet the performance of large language models (LLMs) degrades as context length i
arXiv:2609.37407v1 Announce Type: new Abstract: While recent video foundation models excel at generating high-quality short videos, long-form video generation remains a critical challenge, where a maj
arXiv:2609.37807v1 Announce Type: new Abstract: Studying how fine-tuning shapes refusal and noncompliance behaviour requires identifying training examples that refuse, evade or otherwise fail to fulfi
arXiv:2609.35814v1 Announce Type: cross Abstract: As browser-use agents improve, benchmarks keep pace by collecting new tasks, websites, and applications, often making tasks longer or more novel. This
arXiv:2609.37071v1 Announce Type: new Abstract: Non-rigid point-cloud registration aims to find the corresponding target point for each point on a deforming source surface. Point-level matching keeps
arXiv:2609.37743v1 Announce Type: new Abstract: LLM agents performing long-horizon tasks accumulate tool results that later steps may need. Passing the full history to every invocation is costly even
arXiv:2609.36588v1 Announce Type: cross Abstract: We study reinforcement learning (RL) methods for cooperative multi-agent Vision-Language-Action (VLA) models. This problem is challenging because VLAs
arXiv:2609.38107v1 Announce Type: cross Abstract: Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging, agent auditing, and claims about reasoning.
arXiv:2609.36570v1 Announce Type: cross Abstract: Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that s
arXiv:2609.35823v1 Announce Type: new Abstract: Vision-language models (VLMs) have made substantial progress in autonomous driving, but their success has primarily been studied in ego-centric scenes.
arXiv:2609.37591v1 Announce Type: cross Abstract: Test-time adaptation for vision-language navigation (TTA-VLN) enables pretrained policies to adapt online to unseen environments using only test-time
arXiv:2609.37216v1 Announce Type: cross Abstract: Large language models can generate plausible code-review comments, but such comments may contain technically incorrect claims that mislead developers.
arXiv:2609.37751v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) large language models scale model capacity by routing each token to a small subset of experts. Their routers are regular
arXiv:2609.38087v1 Announce Type: new Abstract: Behavior Foundation Models (BFMs) give humanoids a promptable policy over a latent behavior space, enabling one single vector to represent a motion to i
arXiv:2609.36616v1 Announce Type: new Abstract: Historical street-view imagery records urban evolution, but uneven coverage leaves substantial gaps in historical records. Generating plausible past app
arXiv:2509.06154v3 Announce Type: replace Abstract: Developing accurate, data-efficient surrogate models is central to advancing AI for Science. Neural operators (NOs), which approximate mappings betw
arXiv:2609.37569v1 Announce Type: new Abstract: Rendering accurate Chinese text remains challenging for text-to-image models. Existing OCR-based reinforcement-learning rewards compare decoded transcri
arXiv:2606.20223v2 Announce Type: replace Abstract: Camera-trap monitoring in African tropical forests increasingly extends beyond closed-canopy interiors to riverbanks, clearings, and park edges. Amo
arXiv:2609.36241v1 Announce Type: new Abstract: Dexterous robotic hands typically reproduce human hand morphology but inherit its one-sided grasping workspace, requiring wrist or arm reorientation to
arXiv:2609.37109v1 Announce Type: cross Abstract: The rapid, unpredictable advancements in AI system capabilities has seen regulators take adaptive and experimental approaches to policymaking. Establi
🪽DFlash draft models are available for Ornith-1.5 9B, 35B-A3B, and 397B. DFlash and Ornith 1.5 make a dynamic duo: DFlash performs as the draft model, accelerating inference by drafting multiple token
arXiv:2609.38094v1 Announce Type: new Abstract: Dimensional homogeneity is a fundamental constraint on physically meaningful models, requiring invariance under changes of units. We present a data-driv
arXiv:2609.37398v1 Announce Type: new Abstract: World-Action Models (WAMs) couple action generation with predictions of how physical interactions unfold. However, current post-deployment learning para
arXiv:2609.36630v1 Announce Type: new Abstract: Modern agents increasingly rely on memories, tools, and execution logic, so their competence extends beyond model parameters. This shift exposes a limit
arXiv:2609.36741v1 Announce Type: new Abstract: Under irreversible resource depletion, an agent can spend resources to distinguish among latent fault models, or to change the system state so that the
arXiv:2609.36576v1 Announce Type: new Abstract: Agentic systems are now being widely used to orchestrate tools and reason over long contexts. However, the improving capabilities of the large language
arXiv:2609.38156v1 Announce Type: new Abstract: Distribution matching distillation (DMD) provides a general framework for few-step diffusion generation, but its modern text-to-image instantiations hav
arXiv:2606.18623v2 Announce Type: replace Abstract: Gaussian segmentation is usually posed as transferring object knowledge from 2D foundation models into a 3D representation. This leaves a fundamenta
arXiv:2609.37938v1 Announce Type: cross Abstract: Embodied systems must make knowledge acquired during one encounter usable in another despite changes in viewpoint, motion, and illumination. Yet aggre
arXiv:2609.36842v1 Announce Type: new Abstract: Which layers of a feed-forward geometry model are needed to preserve both camera poses and dense 3D structure? We study layer redundancy in VGGT, pi^3,
arXiv:2609.36395v1 Announce Type: new Abstract: Teams of unmanned aerial vehicles (UAVs) deployed for search and monitoring missions frequently operate as partially connected networks, forcing each ro
arXiv:2609.38025v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on its own generated responses using dense, token-level supervision from a stronger teacher. Vanilla OPD
arXiv:2609.36775v1 Announce Type: new Abstract: Reinforcement Learning has significantly advanced the complex reasoning capabilities of MLLMs. However, prevailing RL algorithms suffer a severe failure
arXiv:2502.04492v3 Announce Type: replace Abstract: The advancement of LLMs and their accessibility have triggered renewed interest in multi-agent reinforcement learning as robust and adaptive framewo
arXiv:2609.36504v1 Announce Type: new Abstract: Accurate prediction of three-dimensional (3D) microstructure evolution remains computationally demanding because high-fidelity phase-field simulations r
arXiv:2609.38046v1 Announce Type: new Abstract: Egocentric human demonstrations offer an accessible source of task experience, but differences in body scale and controller response, together with miss
arXiv:2609.36460v1 Announce Type: cross Abstract: Several tonal pitch spaces and computational models have been proposed to analyze tonal structure in Western tonal music, many of them grounded in pri
arXiv:2609.38157v1 Announce Type: cross Abstract: Emotion-conditioned text-to-speech (TTS) models may fail to express the requested emotion reliably, and improving controllability by additional traini
arXiv:2609.37359v1 Announce Type: cross Abstract: Coding agents can now write, run, and debug programs with little human help. Robot tasks, however, are usually specified by a sentence that leaves out
arXiv:2609.37923v1 Announce Type: new Abstract: Agents can learn from past executions, but enabling different agents to reuse and build on one another's experience remains challenging. We introduce Ep
arXiv:2609.36970v1 Announce Type: new Abstract: The Rashomon effect describes the existence of multiple near-optimal models that achieve comparable performance while offering fundamentally different e
arXiv:2609.35839v1 Announce Type: cross Abstract: Handclaps provide an equipment-free excitation for room acoustics, but their unknown and variable source waveform makes room impulse response (RIR) es
arXiv:2609.37465v1 Announce Type: new Abstract: Counting completed wingbeats requires identifying individual cycles, including during frequency changes and pauses; estimating a dominant frequency alon
arXiv:2512.00329v2 Announce Type: replace-cross Abstract: Temporal reasoning over evolving semi-structured tables poses a challenge to current QA systems. We propose an approach that recasts the task