Knowledge catalogue
arXiv:2605.30190v1 Announce Type: new Abstract: Diffusion-based planning has achieved strong results in single-agent offline reinforcement learning, yet scaling to many-agent systems remains intractab
arXiv:2605.28825v1 Announce Type: new Abstract: Large language models (LLMs) frequently encode factual and reasoning knowledge in their internal representations that is not faithfully reflected in the
arXiv:2603.23234v2 Announce Type: replace Abstract: LLM agents increasingly rely on memory mechanisms to reuse knowledge from past problem-solving experiences. However, existing methods typically cons
arXiv:2604.14889v2 Announce Type: replace Abstract: While chain-of-thought (CoT) reasoning enables LLMs to solve challenging reasoning tasks, the linear growth of the KV cache leads to substantial mem
arXiv:2507.09574v3 Announce Type: replace-cross Abstract: Recent text-to-image models produce high-quality results but still struggle with precise visual control, balancing multimodal inputs, and requ
arXiv:2605.28828v1 Announce Type: cross Abstract: Large Language Models (LLMs) achieve impressive performance across many tasks but remain prone to hallucination, especially in long-form generation wh
arXiv:2605.29512v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as interactive agents, yet their capacity for social and strategic reasoning over extended intera
arXiv:2512.17220v2 Announce Type: replace Abstract: Humans understand long and complex texts by relying on a holistic semantic representation of the content. This global view helps organize prior know
arXiv:2605.30288v1 Announce Type: new Abstract: Mid-training has become an important stage in modern LLM development, using large-scale curated mixtures to strengthen capabilities before final post-tr
arXiv:2507.00037v2 Announce Type: replace-cross Abstract: Model fusion seeks to combine independently trained neural networks into a single model without retraining, but is complicated by representati
arXiv:2605.29101v1 Announce Type: new Abstract: Model merging combines fine-tuned checkpoints into a single multi-task model without retraining. Existing methods - such as task arithmetic, model soups
arXiv:2510.22437v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) solve complex tasks by generating long Chain-of-Thought (CoT) sequences; however, the emergent dynamics governing reas
arXiv:2605.29220v1 Announce Type: new Abstract: Tracking the dynamics of non-canonical biological systems in microscopy videos remains a persistent challenge. Both classical and learning-based tracker
arXiv:2508.08677v2 Announce Type: replace-cross Abstract: Online Class-Incremental Learning (OCIL) enables models to learn continuously from non-i.i.d. data streams. Since samples of the data streams
arXiv:2602.14399v2 Announce Type: replace Abstract: Multi-turn jailbreak attacks have proven effective against text-only large language models (LLMs), where malicious content is gradually introduced t
arXiv:2605.29951v1 Announce Type: new Abstract: Understanding how harm emerges from interaction between otherwise benign image-text pairs requires intent-aware cross-modal reasoning beyond surface-lev
arXiv:2605.29716v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive generative paradigm. Given the prohibitive computational cost of
arXiv:2505.05968v3 Announce Type: replace Abstract: Offline cooperative multi-agent reinforcement learning (MARL) faces unique challenges due to distributional shifts, particularly stemming from the h
arXiv:2510.11499v2 Announce Type: replace-cross Abstract: Generative models have emerged as a powerful class of policies for offline reinforcement learning (RL) due to their ability to capture complex
arXiv:2511.08423v3 Announce Type: replace Abstract: A truly universal AI-Generated Image (AIGI) detector must simultaneously generalize across diverse generative models and varied semantic content. Cu
arXiv:2605.30168v1 Announce Type: new Abstract: Change detection (CD) in remote sensing is vital for applications such as urban monitoring and disaster assessment, yet traditional methods struggle wit
arXiv:2605.29250v1 Announce Type: cross Abstract: Real-world information needs require access to structurally diverse knowledge sources, from unstructured text and relational tables to knowledge graph
arXiv:2605.29495v1 Announce Type: new Abstract: Continual supervised fine-tuning (SFT) is the de facto recipe for adapting large language models (LLMs) to a stream of downstream tasks, but it suffers
arXiv:2605.29580v1 Announce Type: new Abstract: While parameter-efficient fine-tuning methods like low-rank adaptation (LoRA) are standard for large language models, principled estimation of epistemic
arXiv:2605.29556v1 Announce Type: new Abstract: Building mathematical optimization models is critical in operations research (OR), while it requires substantial human expertise. Recent advancements ha
arXiv:2605.29575v1 Announce Type: new Abstract: Rapid identification of damaged buildings after natural disasters or on war areas is crucial to support emergency response and prioritize interventions.
arXiv:2605.06355v2 Announce Type: replace Abstract: Order-Agnostic autoregressive models have demonstrated strong performance in deep generative modeling, yet their use in settings with incomplete dat
arXiv:2605.29900v1 Announce Type: new Abstract: Contrastive learning is effective for aligning paired views or modalities, but alignment beyond two modalities remains non-trivial and comparatively und
arXiv:2605.29157v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become the central paradigm in artificial intelligence, yet the core computational primitive of attention has remain
arXiv:2605.30126v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) map visual inputs into dense token sequences, imposing a quadratic computational bottleneck for inference. Elasti
arXiv:2605.29357v1 Announce Type: new Abstract: Modern tensor compilers such as TorchInductor deliver substantial speedups on mainstream models, yet face a systematic performance ceiling on long-tail
arXiv:2605.29582v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown promise as educational tutors, yet effective tutoring requires more than solving problems: it must provide pro
arXiv:2605.29299v1 Announce Type: cross Abstract: Evaluations of dental vision-language models remain fragmented across datasets, task definitions and metrics, and often ignore their computational cos
arXiv:2605.30094v1 Announce Type: new Abstract: Poker is a landmark challenge for artificial intelligence. The dominant approach relies on equilibrium solvers built on counterfactual regret minimizati
arXiv:2605.29631v1 Announce Type: cross Abstract: Randomized controlled trials are a cornerstone of medicine and the social sciences as they enable reliable estimates of causal effects. However, they
arXiv:2509.08194v2 Announce Type: replace Abstract: We address the problem of policy selection in contextual stochastic optimization (CSO), where covariates are available as contextual information and
arXiv:2605.28867v1 Announce Type: cross Abstract: Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, includin
arXiv:2605.29119v1 Announce Type: new Abstract: Computer use agents (CUAs) have shown strong potential for automating complex digital workflows, yet their training remains constrained by costly live e
arXiv:2605.29172v1 Announce Type: new Abstract: Seasonal climate predictions support planning and risk management by offering early information of the most likely-to-occur climate conditions in the co
arXiv:2605.29275v1 Announce Type: new Abstract: Open-ended post-training benefits from rewards that make prompt-specific success conditions explicit, rather than relying only on post-hoc scalar scores
arXiv:2605.29158v1 Announce Type: new Abstract: Protein homology search underlies function annotation, structure prediction, and evolutionary analysis, but remains challenging in the 'twilight zone,'
arXiv:2605.30280v1 Announce Type: cross Abstract: Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented cap
arXiv:2605.30029v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems expose numerous design choices spanning query rewriting, chunking, retrieval depth, reranking, and context
arXiv:2605.29114v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models with integrated reasoning have been proposed for end-to-end autonomous driving, assuming a tight coupling between
arXiv:2602.00994v2 Announce Type: replace Abstract: Agentic Reinforcement Learning (ARL) trains large language models to interleave reasoning with external tool execution to solve complex tasks. Most
arXiv:2605.29327v1 Announce Type: new Abstract: Efficient Distillation (EDistill) compresses large language models (LLMs) by structured pruning parameters and tuning lightweight modules with high trai
arXiv:2602.01456v2 Announce Type: replace-cross Abstract: Joint-Embedding Predictive Architectures (JEPA) learn view-invariant representations and admit projection-based distribution matching for coll
arXiv:2605.30244v1 Announce Type: cross Abstract: While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partial
arXiv:2605.29224v1 Announce Type: cross Abstract: AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating
arXiv:2605.30052v1 Announce Type: cross Abstract: One-shot Program-of-Thought (PoT) emits a Python program that prints a primitive-action plan; a single invalid action silently invalidates the traject
arXiv:2601.21564v2 Announce Type: replace Abstract: Machine unlearning seeks to remove the influence of specific training data from a model, a need driven by privacy regulations and robustness concern
arXiv:2510.00936v2 Announce Type: replace Abstract: Cross-resolution person re-identification (CR-ReID) remains challenging in practical surveillance, where camera quality and capture distance lead to
arXiv:2605.29335v1 Announce Type: cross Abstract: Frechet Inception Distance (FID) is widely used to evaluate image generators, yet lower FID does not always correspond to better sample quality. We sh
arXiv:2605.29234v1 Announce Type: new Abstract: We study large-scale literature search from two complementary angles: improving the retrieval pipeline, and stress-testing the human reference list as a
arXiv:2605.29401v1 Announce Type: new Abstract: Time-Series Foundation Models (TSFMs) excel at zero-shot unimodal forecasting using numerical data, but unlike LLMs they cannot consume multimodal, non-
arXiv:2605.29319v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance on table reasoning tasks but incur substantial inference cost due to long reasoning traces. Ste
arXiv:2605.29028v1 Announce Type: cross Abstract: Conditioned Sequence Models (CSMs) learn policies by treating return-to-go (RTG) as a control signal. However, existing CSMs often treat the RTGs as s
arXiv:2605.29397v1 Announce Type: new Abstract: HTML observations in LLM-based web agents are extremely long, and while many reduction methods have been proposed, it remains unclear which methods redu
arXiv:2603.18859v2 Announce Type: replace Abstract: Reinforcement learning (RL) shows promise for enhancing LLM agentic reasoning, yet sparse terminal rewards hinder fine-grained optimization. Process
arXiv:2603.27758v2 Announce Type: replace Abstract: Metric Cross-View Geo-Localization (MCVGL) aims to estimate the 3-DoF camera pose (position and heading) by matching ground and satellite images. In