Knowledge catalogue
arXiv:2602.01166v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models benefit from chain-of-thought (CoT) reasoning, but existing approaches incur high inference overhead and rely on
arXiv:2605.07315v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning improves large language models (LLMs) on difficult tasks, but it also makes inference expensive because every intermedi
arXiv:2605.07180v1 Announce Type: new Abstract: LLM agents achieve strong performance on complex reasoning tasks but incur high latency and compute cost. In practice, many queries fall within the capa
arXiv:2605.06957v1 Announce Type: new Abstract: We present a dynamic policy-learning approach that combines generalized planning and hierarchical task decomposition for LLM-based agents. Our method, H
arXiv:2605.07038v1 Announce Type: new Abstract: Risk-aware navigation should be selective: a policy should expose evasive degrees of freedom only when the local scene admits a lower-risk feasible mane
arXiv:2511.09907v5 Announce Type: replace Abstract: Data synthesis for training large reasoning models offers a scalable alternative to limited, human-curated datasets, enabling the creation of high-q
arXiv:2605.07064v1 Announce Type: new Abstract: How to achieve vision-language (VL) tracking using natural language descriptions from a video sequence extbf{without relying on any bounding-box ground
arXiv:2605.07019v1 Announce Type: cross Abstract: Vision Language Models (VLMs) offer the exciting possibility of processing text as rendered images, bypassing the need for tokenizing the text into lo
arXiv:2605.07505v1 Announce Type: new Abstract: Developing lightweight, on-device vision-language GUI agents is essential for efficient cross-platform automated interaction. However, current on-device
arXiv:2605.06676v1 Announce Type: cross Abstract: Long-context inference in Large Language Models (LLMs) is bottlenecked by the linear growth of Key-Value (KV) cache memory. Existing KV cache compress
arXiv:2601.21424v3 Announce Type: replace-cross Abstract: Many computer vision tasks share substantial overlapping information, yet conventional codecs tend to ignore this, leading to redundant and in
arXiv:2605.05225v2 Announce Type: replace-cross Abstract: Mixture-of-Experts Multimodal Large Language Models (MoE MLLMs) suffer from a significant efficiency bottleneck during Expert Parallelism (EP)
arXiv:2605.07342v1 Announce Type: cross Abstract: Compile-pass rate is the dominant evaluation signal for LLM code generation, yet for multi-component domain-specific artifacts it can be actively misl
arXiv:2507.21183v5 Announce Type: replace-cross Abstract: As the era of large language models (LLMs) unfolds, Preference Optimization (PO) methods have become a central approach to aligning LLMs with
arXiv:2605.05949v2 Announce Type: replace Abstract: Algorithmic problem solving serves as a rigorous testbed for evaluating structured reasoning in AI coding systems, as it directly reflects a model's
arXiv:2605.07280v1 Announce Type: cross Abstract: Leveraging deep learning for causal discovery in time series remains challenging because existing neural methods predominantly rely on component-wise
arXiv:2602.20974v2 Announce Type: replace Abstract: In engineering design and scientific computing, computational cost and predictive accuracy are intrinsically coupled. High-fidelity simulations prov
arXiv:2605.07600v1 Announce Type: cross Abstract: Recent methods for improving LLM mathematical reasoning, whether through MCTS-based test-time search or causal graph-guided knowledge injection, canno
arXiv:2605.07646v1 Announce Type: cross Abstract: While explicit reasoning trajectories enhance model interpretability, existing paradigms often rely on monolithic chains that lack intermediate verifi
arXiv:2605.07305v1 Announce Type: cross Abstract: Most existing LLM diagnoses are evaluated on static, single-turn settings where complete patient information is provided upfront, an oversimplificatio
arXiv:2605.07058v1 Announce Type: cross Abstract: Real-world clinical diagnosis is a complex process in which the doctor is required to obtain information from both interaction with the patient and co
arXiv:2605.07919v1 Announce Type: new Abstract: Medical vision--language models (VLMs) are usually evaluated on intact image--question pairs, but trustworthy clinical use requires a stronger property:
arXiv:2605.06903v1 Announce Type: cross Abstract: Large language models are now embedded in everyday writing workflows, making reliable AI-generated text detection important for academic integrity, co
arXiv:2602.06523v2 Announce Type: replace Abstract: Human Activity Recognition (HAR) on resource constrained wearables requires models that balance accuracy against strict memory and computational bud
arXiv:2605.06797v1 Announce Type: new Abstract: We propose the Monge Inception Distance (MIND), a metric for evaluating generative models that addresses key limitations of the widely adopted Frechet I
arXiv:2605.07550v1 Announce Type: new Abstract: 3D vision systems are fundamentally constrained by their reliance on visual overlap: reconstruction methods require it for geometric alignment, while ge
arXiv:2601.04731v2 Announce Type: replace Abstract: Current critic-free RL methods for large reasoning models suffer from severe inefficiency when training on positive homogeneous prompts (where all r
arXiv:2602.00513v3 Announce Type: replace Abstract: Cyber threat intelligence (CTI) analysts routinely convert noisy, unstructured security artifacts into standardized, automation-ready representation
arXiv:2605.07269v1 Announce Type: new Abstract: Indirect prompt injection remains a persistent weakness in retrieval-augmented and tool-using LLM systems, and the problem becomes harder to characteris
arXiv:2605.07520v1 Announce Type: new Abstract: Differentiable planning enables gradient-based optimization of decision-making problems by leveraging differentiable models of system dynamics. However,
arXiv:2603.18856v2 Announce Type: replace-cross Abstract: Recent video reasoning models increasingly produce spatio-temporal evidence chains that localize objects at specific timestamps. While these t
arXiv:2605.07537v1 Announce Type: new Abstract: Partially Observable Markov Decision Processes (POMDPs) are systems in which one agent interacts with a stochastic environment, and receives only partia
arXiv:2605.06951v1 Announce Type: new Abstract: Constraint inference is widely considered essential to align reinforcement learning agents with safety boundaries and operational guidelines by observin
arXiv:2605.08078v1 Announce Type: new Abstract: Diffusion-based models decompose sampling into many small Gaussian denoising steps -- an assumption that breaks down when generation is compressed to a
arXiv:2605.07660v1 Announce Type: new Abstract: Reinforcement-learning-based post-training has become a key approach for improving the reasoning ability of large language models, but its token-level l
arXiv:2605.07476v1 Announce Type: new Abstract: Multivariate time series forecasting remains a challenge due to the complexity of local temporal dynamics and global dependencies across multiple variab
arXiv:2508.01248v4 Announce Type: replace Abstract: The rapid progress of generative models, such as GANs and diffusion models, has facilitated the creation of highly realistic images, raising growing
arXiv:2604.03675v2 Announce Type: replace Abstract: Agentic search enables language models to solve knowledge-intensive tasks by adaptively acquiring external evidence over multiple steps. Reinforceme
arXiv:2605.07393v1 Announce Type: new Abstract: A fundamental challenge in model-based offline reinforcement learning (RL) lies in the trade-off between generalization and robustness against exploitat
One of the most important properties of LLMs that we take for granted is that newer, bigger models are just better at everything. The AI Labs are pouring effort into economically valuable fields like
arXiv:2605.06993v1 Announce Type: new Abstract: Causal queries are often only partially identifiable from observational data, and experiments that could tighten the resulting bounds are typically cost
arXiv:2603.04678v2 Announce Type: replace-cross Abstract: Large language models are known to often exhibit inconsistent knowledge. This is particularly problematic in multilingual scenarios, where mod
arXiv:2602.00465v3 Announce Type: replace-cross Abstract: Functional miRNA--mRNA targeting is a large-bag prediction problem where each transcript yields a heavy-tailed pool of candidate target sites
arXiv:2605.07248v1 Announce Type: new Abstract: Beyond training-time optimization, scaling test-time computation has emerged as a key paradigm to extend the reasoning capabilities of Large Language Mo
arXiv:2605.07496v1 Announce Type: new Abstract: Bird's-eye-view (BEV) images have been widely demonstrated to provide valuable prior information for navigation. Given the global information provided b
arXiv:2605.07267v1 Announce Type: new Abstract: Personalized healthcare decisions require reasoning about how physiological and behavioral variables influence an individual patient over time. Existing
arXiv:2512.14018v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have achieved remarkable progress in automatic code generation, yet their ability to produce high-performance cod
arXiv:2605.07467v1 Announce Type: cross Abstract: Existing interventional causal discovery methods -- IGSP, DCDI, ENCO -- assume causal sufficiency (no latent confounders) and rely on virtual interven
arXiv:2605.07687v1 Announce Type: new Abstract: Physics-based digital twins aim to predict the dynamics of real-world objects under interaction, enabling real-to-sim-to-real applications in robotics.
arXiv:2605.07215v1 Announce Type: new Abstract: Stochastic trajectory optimization methods like STOMP enable planning with non-differentiable costs, offering substantial flexibility over gradient-base
arXiv:2605.07574v1 Announce Type: new Abstract: Mainstream vision-language models (VLMs) fundamentally struggle with severe optical ambiguities, such as reflections and transparent objects, due to the
arXiv:2605.07154v1 Announce Type: new Abstract: Referring Audio-Visual Segmentation (Ref-AVS) seeks to localize and segment target objects in video frames based on visual, auditory, and textual referr
arXiv:2605.08064v1 Announce Type: new Abstract: Spatial intelligence in vision-language models (VLMs) attracts research interest with the practical demand to reason in the 3D world.Despite promising r
arXiv:2605.07804v1 Announce Type: cross Abstract: On-policy distillation (OPD) leverages dense teacher rewards to enhance reasoning models. However, scaling OPD to long-horizon tasks exposes a critica
arXiv:2605.07375v1 Announce Type: new Abstract: Normalization layers in neural operators usually compute statistics by uniformly averaging discrete grid values, making the normalization itself discret
arXiv:2605.07663v1 Announce Type: cross Abstract: Data valuation methods allocate payments and audit training data's contribution to machine-learning pipelines; however, they often assume passive cont
arXiv:2605.06483v2 Announce Type: replace Abstract: Signal Temporal Logic (STL) is an expressive formal language for specifying spatio-temporal requirements over real-valued, real-time signals. It has
arXiv:2408.06747v4 Announce Type: replace Abstract: Recent works utilize CLIP to perform the challenging unsupervised semantic segmentation task where only images without annotations are available. Ho
arXiv:2605.07234v1 Announce Type: cross Abstract: Large language models (LLMs) support long-context inference but suffer from substantial memory and runtime overhead due to Key-Value (KV) Cache growth
arXiv:2605.07134v1 Announce Type: cross Abstract: Web agents perceive web pages through an observation space, yet its granularity has remained an underexamined design choice. Existing work treats obse