Knowledge catalogue
arXiv:2605.14354v1 Announce Type: new Abstract: We present a new computational framework for detecting and structuring manipulative political narratives. A task that became more important due to the s
arXiv:2605.14292v1 Announce Type: cross Abstract: KV-cache compression at small budgets is a crowded design space spanning cache representation, head-wise routing, compression cadence, decoding behavi
arXiv:2605.14111v1 Announce Type: new Abstract: Hospital pharmacists make high-stakes decisions to mitigate drug shortages under uncertainty, time pressure, and patient risk. Interviews revealed that
arXiv:2605.14666v1 Announce Type: new Abstract: Dynamic systems in AI are often complex and heterogeneous, so that an internal specification is not accessible and verification techniques such as model
arXiv:2603.23129v2 Announce Type: replace Abstract: Godel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop. We intro
arXiv:2603.12554v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has been effective for post-training autoregressive (AR) language models, but extending these methods to diffusion
arXiv:2605.14866v1 Announce Type: cross Abstract: As modern microservice systems grow increasingly complex due to dynamic interactions and evolving runtime environments, they experience failures with
arXiv:2605.14192v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become a powerful and widely used approach for improving large language models by grounding generation in ret
arXiv:2605.12586v1 Announce Type: cross Abstract: Vision-language models (VLMs) exhibit a striking paradox: they can generate executable code that reconstructs a 3D scene from geometric primitives wit
arXiv:2605.12622v1 Announce Type: cross Abstract: We formalize action emergence as a target capability for end-to-end autonomous driving: the ability to generate physically feasible, semantically appr
arXiv:2605.12954v1 Announce Type: cross Abstract: Long video understanding is heavily bottlenecked by a rigid one-shot paradigm: existing methods either densely encode videos at prohibitive memory and
arXiv:2605.13360v1 Announce Type: new Abstract: There is a growing demand for agentic AI technologies for a range of downstream applications like customer service and personal assistants. For applicat
arXiv:2601.22868v3 Announce Type: replace Abstract: Anomaly detection usually assumes that abnormality is an intrinsic property of an observation. A defect is a defect, and a rare object is rare, rega
arXiv:2605.12788v1 Announce Type: new Abstract: Sustained effort is essential for realizing the benefits of intelligent tutoring systems (ITS), yet many learners disengage or underuse available practi
arXiv:2605.12944v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) data selection is commonly formulated as instance ranking: score each example and retain a top-k subset. However, effective
arXiv:2506.11274v2 Announce Type: replace-cross Abstract: Test-time scaling has emerged as an effective approach for improving language model performance by utilizing additional compute at inference t
arXiv:2605.12703v1 Announce Type: cross Abstract: We introduce MMCL-Bench, a benchmark for multimodal context learning: learning task-local rules, procedures, and empirical patterns from visual or mix
arXiv:2605.12691v1 Announce Type: new Abstract: Progression, the task of updating a knowledge base to reflect action effects, generally requires second-order logic. Identifying first-order special cas
arXiv:2605.13369v1 Announce Type: cross Abstract: Large language models (LLMs) are typically deployed with fixed parameters, and their performance is often improved by allocating more computation at i
arXiv:2605.13542v1 Announce Type: new Abstract: Intensive care units (ICU) generate long, dense and evolving streams of clinical information, where physicians must repeatedly reassess patient states u
arXiv:2605.13117v1 Announce Type: cross Abstract: Achieving reliable robotic manipulation, such as dexterous grasping, requires a synergy between physically stable interactions and semantic task guida
arXiv:2509.21543v3 Announce Type: replace Abstract: Large Language Models (LLMs) have shown strong promise for robotic task planning, particularly through the automatic generation of symbolic planning
arXiv:2605.13340v1 Announce Type: new Abstract: Shortcut mitigation strategies commonly rely on training data annotations, group-balanced held-out data or the presence of all groups, i.e., all combina
arXiv:2605.12645v1 Announce Type: cross Abstract: Effective personalized question answering (PQA) in language models requires grounding responses in the user's underlying intent, where intent refers t
arXiv:2605.13601v1 Announce Type: new Abstract: As intelligent systems are increasingly implemented in our society to make autonomous decisions, their commitment to human values raises serious concern
arXiv:2602.22474v2 Announce Type: replace-cross Abstract: Policy steering is an emerging way to adapt robot behaviors at deployment-time: a learned verifier analyzes low-level action samples proposed
arXiv:2506.02084v2 Announce Type: replace Abstract: We address the problem of generating simulated, yet realistic, time-series data from a causal model with the same observational and interventional d
arXiv:2605.12495v1 Announce Type: new Abstract: In this paper, we propose AlphaGRPO, a novel framework that applies Group Relative Policy Optimization (GRPO) to AR-Diffusion Unified Multimodal Models
arXiv:2508.07642v3 Announce Type: replace-cross Abstract: Vision-and-Language Navigation (VLN) poses significant challenges for agents to interpret natural language instructions and navigate complex 3
arXiv:2605.11723v1 Announce Type: new Abstract: In this paper, we propose Concentrate and Concentrate (CaC), a coarse-to-fine anomaly reward model based on Vision-Language Models. During inference, it
arXiv:2605.12370v1 Announce Type: new Abstract: While Large Language Models (LLMs) are widely used in open-domain Question Answering (QA), their ability to handle inferential questions-where answers m
arXiv:2605.11260v1 Announce Type: new Abstract: Knowledge distillation is a key technique for transferring the capabilities of large language models (LLMs) into smaller, more efficient student models.
arXiv:2605.11613v1 Announce Type: new Abstract: On-policy self-distillation has emerged as a promising paradigm for post-training language models, in which the model conditions on environment feedback
arXiv:2605.11951v1 Announce Type: new Abstract: Although robotic manipulation has made significant progress, reliable execution remains challenging because task failures are inevitable in dynamic and
arXiv:2605.12309v1 Announce Type: new Abstract: The development of separate-encoder Unified multimodal models (UMMs) comes with a rapidly growing inference cost due to dense visual token processing. I
arXiv:2605.11208v1 Announce Type: new Abstract: Automated, clinician-grade assessment reports for surgical procedures could reduce documentation burden and provide objective feedback, yet remain chall
arXiv:2605.11663v1 Announce Type: new Abstract: Authentic school examinations provide a high-validity test bed for evaluating multimodal large language models (MLLMs), yet benchmarks grounded in Japan
arXiv:2605.12313v1 Announce Type: new Abstract: Multi-hop question answering (QA) remains a significant challenge in the biomedical domain, requiring systems to integrate information across multiple s
arXiv:2605.05749v2 Announce Type: replace Abstract: Dense 3D reconstruction from continuous image streams requires both accurate geometric aggregation and stable long-term memory management. Recent fe
arXiv:2605.12384v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities, but they still frequently produce hallucinations. These hallucinations are diffi
arXiv:2605.12237v1 Announce Type: new Abstract: Vision-Language Models (VLMs) increasingly operate on ultra-high-resolution (UHR) Earth observation imagery, yet they remain vulnerable to a severe scal
arXiv:2605.09115v1 Announce Type: cross Abstract: Modern security environments generate fragmented signals across cloud resources, identities, configurations, and third-party security tools. Although
arXiv:2605.08416v1 Announce Type: new Abstract: Jurisprudence, the study of how judges should properly decide cases, and alignment, the science of getting AI models to conform to human values, share a
arXiv:2605.09268v1 Announce Type: cross Abstract: Users interacting with Large Language Models (LLMs) in a multi-turn conversation routinely refine their requests or pivot to new topics. LLMs, however
arXiv:2605.09146v1 Announce Type: new Abstract: Humanoid Visual Search (HVS) requires agents to actively explore immersive 360^irc environments. While prior methods treat this as a monolithic task rel
arXiv:2511.21104v3 Announce Type: replace Abstract: Large language models can generate plausible code, but remain brittle for formal verification in proof assistants such as Lean. A central scalabilit
arXiv:2605.09253v1 Announce Type: cross Abstract: While recent work in Reinforcement Learning with Verifiable Rewards (RLVR) has shown that a small subset of critical tokens disproportionately drives
arXiv:2605.10488v1 Announce Type: cross Abstract: Agent-compiled knowledge bases provide persistent external knowledge for large language model (LLM) agents in open-ended, knowledge-intensive downstre
arXiv:2605.08462v1 Announce Type: cross Abstract: Hallucination remains a persistent challenge in Large Language Models (LLMs), particularly in context-grounded settings such as RAG and agentic AI sys
arXiv:2605.09693v1 Announce Type: cross Abstract: Yes. We find that large multimodal models develop mental imagery when solving spatial puzzles, and they do imagine sheep when solving sheep puzzles. W
arXiv:2506.08136v3 Announce Type: replace Abstract: We introduce EconWebArena, a benchmark for evaluating autonomous agents on complex, multimodal economic tasks in realistic web environments. The ben
arXiv:2605.09852v1 Announce Type: new Abstract: Machine learning algorithms are being used in high-stakes decisions, including those in criminal justice, healthcare, credit, and employment. The resear
arXiv:2509.20863v3 Announce Type: replace Abstract: Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approa
arXiv:2603.12275v1 Announce Type: cross Abstract: Unlearning knowledge is a pressing and challenging task in Large Language Models (LLMs) because of their unprecedented capability to memorize and dige
arXiv:2605.10762v1 Announce Type: cross Abstract: Long-video understanding in VLMs is bottlenecked by a single monolithic forward pass over thousands of frames at quadratic attention cost. A common mi
arXiv:2605.08330v1 Announce Type: new Abstract: We present a hierarchical language-driven framework for robotic task and motion planning to improve natural, intuitive human-robot interaction in servic
arXiv:2605.10224v1 Announce Type: new Abstract: Current AI-powered research systems adopt a direct search-then-summarize paradigm that treats hypotheses as end products of scientific discovery. We arg
arXiv:2605.09494v1 Announce Type: cross Abstract: Unmanned underwater vehicles (UUVs) operate persistently in communication-constrained environments, thus requiring high-level autonomous fault-toleran
arXiv:2605.10810v1 Announce Type: new Abstract: We introduce an automatically generated benchmark for predicting hidden text in technical papers. A paper supplies visible context X and a hidden contin
arXiv:2503.14434v3 Announce Type: replace-cross Abstract: Automated feature engineering plays a critical role in improving predictive model performance for tabular learning tasks. Traditional automate