Knowledge catalogue
arXiv:2609.08217v1 Announce Type: new Abstract: VLMs have shown promise for autonomous driving, yet still suffer from hallucination, weak spatio-temporal perception, and limited generalization. Recent
arXiv:2609.06779v1 Announce Type: new Abstract: Drug repurposing aims to identify new therapeutic uses for existing compounds and, compared with de novo drug discovery, offers a faster and more cost-e
arXiv:2503.11006v3 Announce Type: replace Abstract: Vision and Language Navigation (VLN) requires an embodied agent to traverse complex environments by following natural language instructions, demandi
GPT‑6 Astra is OpenAI’s latest flagship model, outperforming GPT‑5.6 across virtually all common benchmarks—most noticeably in math, coding, and especially 3‑D rendering/animation tasks. The architect
arXiv:2609.06475v1 Announce Type: new Abstract: Large vision-language models (LVLMs) have recently achieved remarkable progress in general-purpose video understanding. However, their application to su
arXiv:2609.05257v1 Announce Type: new Abstract: Commonsense reasoning in computer vision encompasses integrating visual data and contextual knowledge, crucial for enhancing AI's understanding of every
arXiv:2609.04893v1 Announce Type: new Abstract: Vision-language-action (VLA) models are trained by imitation and capture what action to take but not why; adding causal reasoning improves manipulation,
arXiv:2609.04083v1 Announce Type: cross Abstract: MLLM-based embedding models remain limited in compositional retrieval, often failing to distinguish scenes containing the same concepts but different
arXiv:2609.03816v1 Announce Type: cross Abstract: Graphs are a fundamental data structure underlying many problems in the natural and social sciences. Over the past decade, Graph Neural Networks (GNNs
arXiv:2603.19539v2 Announce Type: replace-cross Abstract: We introduce an expert curated, real-world benchmark for evaluating document-grounded question-answering (QA) motivated by generic drug assess
Next year frontier models are going to one shot everything 100x faster & cheaper than they are No reasoning traces to monitor Instinctive intelligence Which is why what you embed in pretraining is eve
arXiv:2607.27287v2 Announce Type: replace Abstract: Planning over Temporal Dynamic Knowledge Graphs (TDKGs) presents theoretical challenges in open-world environments with incomplete information. Exis
arXiv:2609.00342v1 Announce Type: new Abstract: Whole-slide images (WSIs) are challenging for vision-language reasoning because diagnostically relevant morphology is sparse, heterogeneous, and distrib
arXiv:2602.06449v2 Announce Type: replace Abstract: Privacy and computational constraints limit the use of large language models in psychiatry, while adapting small language models (SLMs) often requir
arXiv:2608.30250v1 Announce Type: new Abstract: This paper addresses the problem of translating natural-language routing rules written by business administrators into executable workflow graphs for en
arXiv:2608.30632v1 Announce Type: cross Abstract: Reinforcement learning (RL), particularly RL with Verifiable Rewards (RLVR), has recently emerged as a central paradigm for enhancing large language m
arXiv:2608.29783v1 Announce Type: new Abstract: Industrial anomaly detection is a critical component of modern manufacturing. Most traditional unsupervised methods rely on modelling normal feature dis
arXiv:2608.30676v1 Announce Type: new Abstract: When medical AI systems hallucinate clinical reasoning, the consequences extend beyond incorrect answers: fabricated justifications that superficially r
arXiv:2608.28675v1 Announce Type: cross Abstract: Video reasoning tasks such as grounded video question answering and temporal grounding require selecting temporal evidence that supports the query. In
arXiv:2608.30399v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong semantic reasoning and open-ended generation abilities, but aligning these abilities with structured seque
arXiv:2608.28155v1 Announce Type: new Abstract: Professional financial examinations require models to combine domain knowledge, calculation, and judgment, yet no benchmark covers the full CFA and FRM
arXiv:2608.27756v1 Announce Type: new Abstract: Determining whether large language models derive answers from context or prior knowledge remains a fundamental challenge. Self-contained linguistic olym
arXiv:2608.26386v1 Announce Type: cross Abstract: Retrieval-augmented methods improve factual accuracy by grounding language models in external knowledge, but retrieving over unstructured text often i
arXiv:2604.05876v2 Announce Type: replace Abstract: Deploying Large Language Models (LLMs) in real-world dynamic environments raises the challenge of updating their pre-trained knowledge. While existi
arXiv:2608.25531v1 Announce Type: new Abstract: Humanities and social science research requires close reading of long narrative materials such as novels, scripts, archives, and case reports, yet many
arXiv:2608.24959v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models encode visual observations as flat 2D patch tokens that carry no intrinsic geometric structure, and augmenting the
arXiv:2608.24338v1 Announce Type: new Abstract: Inference-time decoding methods improve LLM reasoning by exploring multiple candidate trajectories, yet treat each trajectory as atomic: either retainin
arXiv:2602.09555v3 Announce Type: replace Abstract: Recent advances in block diffusion language models have demonstrated competitive performance and strong scalability on reasoning tasks. However, the
arXiv:2608.22126v1 Announce Type: cross Abstract: Physics reasoning requires constructing a consistent model of the underlying physical system rather than relying solely on symbolic or formula-based m
arXiv:2608.22566v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems are designed to improve reasoning by decomposing tasks across multiple agents with specialized functions,
arXiv:2608.21863v1 Announce Type: cross Abstract: Tool-Integrated Reasoning (TIR) is a fundamental capability for LLM agents to solve complex tasks by interacting with external tools iteratively. Rein
arXiv:2608.22140v1 Announce Type: cross Abstract: Large Language Models (LLMs) achieve strong reasoning performance, but their robustness to realistic lexical corruption remains poorly understood. We
arXiv:2608.22785v1 Announce Type: new Abstract: Spatial multi-omics technologies jointly profile gene expression, surface proteins, and histology at each tissue spot, yet most spatial domain discovery
arXiv:2608.20814v1 Announce Type: new Abstract: Though Multimodal Large Language Models (MLLMs) have shown impressive potential in video understanding, long video understanding (LVU) remains challengi
arXiv:2608.18242v1 Announce Type: new Abstract: We introduce ClosureBench, a constructive benchmark for compositional graph-relational reasoning with programmatically verified ground truth. Unlike fix
arXiv:2608.18078v1 Announce Type: new Abstract: This position paper argues that AI agents with chain-of-thought reasoning capabilities are predisposed to exhibit collusive behavior and should be requi
arXiv:2608.17301v1 Announce Type: new Abstract: Post-training with supervised chain-of-thought fine-tuning and reinforcement learning from verifiable rewards has substantially improved the mathematica
arXiv:2608.16554v1 Announce Type: new Abstract: Answer-only reinforcement learning (RL) trains reasoning models to solve fully specified problems, but many realistic queries omit a premise needed for
arXiv:2608.14791v1 Announce Type: new Abstract: Abductive reasoning, often characterized as inference to the best explanation, is central to explanation under uncertainty, from everyday sense-making a
arXiv:2608.15303v1 Announce Type: new Abstract: Test-time compute can substantially improve Large Language Model (LLM) reasoning performance, yet how and when additional compute helps remains poorly u
arXiv:2608.15517v1 Announce Type: new Abstract: Chain-of-thought reasoning has substantially improved the problem-solving capabilities of multimodal large language models. Fine-grained visual evidence
arXiv:2608.15673v1 Announce Type: cross Abstract: Large language model guardrails can be viewed as policy-consistency problems: a system must determine which policy-relevant facts hold in a prompt-res
arXiv:2603.06697v2 Announce Type: replace-cross Abstract: Vision--language models (VLMs) process images as visual tokens, yet their intermediate reasoning is often carried out in text, which can be su
arXiv:2608.13309v1 Announce Type: new Abstract: Magnetic Resonance Imaging (MRI) interpretation is fundamental to clinical decision-making, requiring radiologists to integrate multi-view anatomical pl
arXiv:2608.13095v1 Announce Type: cross Abstract: Training and evaluating spatial reasoning in embodied agents requires diverse environments that are both geometrically faithful and semantically query
arXiv:2608.11150v1 Announce Type: new Abstract: While 3D Gaussian Splatting (3DGS) has advanced open vocabulary scene understanding, existing methods remain confined to explicit queries. They struggle
arXiv:2608.10317v1 Announce Type: new Abstract: We present TAR (Traffic Anomaly Reasoning) and TAR-Bench datasets, resources for training and evaluating video-language models beyond anomaly detection.
arXiv:2505.23399v2 Announce Type: replace Abstract: We propose GAM-Agent, a game-theoretic multi-agent framework for enhancing vision-language reasoning. Unlike prior single-agent or monolithic models
arXiv:2601.10129v2 Announce Type: replace-cross Abstract: Current multimodal latent reasoning often relies on external supervision (e.g., auxiliary images), ignoring intrinsic visual attention dynamic
arXiv:2608.10420v1 Announce Type: new Abstract: Reasoning shortcuts are solutions of a neurosymbolic system's rules that produce correct predictions through unintended concepts. A recent framework of
arXiv:2509.25143v2 Announce Type: replace-cross Abstract: Existing medical reasoning benchmarks for vision-language models primarily focus on analyzing a patient's condition based on an image from a s
arXiv:2608.10981v1 Announce Type: new Abstract: Task-driven 3D affordance grounding aims to localize the functional region in a cluttered 3D scene that enables an action specified by a natural-languag
arXiv:2608.09942v1 Announce Type: cross Abstract: It is widely assumed that chain-of-thought (CoT) prompting universally improves LLM reasoning. We investigate this through the conceptual framework of
arXiv:2608.07838v1 Announce Type: new Abstract: Large language models (LLMs) have increasingly supported response generation grounded in user-provided knowledge spanning heterogeneous structures. Howe
arXiv:2608.08447v1 Announce Type: cross Abstract: Multilingual reasoning models are commonly evaluated by whether they arrive at the correct answer, but not by whether they preserve the intended langu
arXiv:2608.08623v1 Announce Type: new Abstract: In Reinforcement Learning with Verifiable Rewards (RLVR) frameworks for mathematical reasoning tasks, floating-point results are typically evaluated usi
arXiv:2608.07959v1 Announce Type: new Abstract: Ultra-long egocentric video understanding requires reasoning over temporally sparse evidence distributed across hours or days, challenging current multi
arXiv:2608.08640v1 Announce Type: new Abstract: Large language model agents increasingly rely on reusable skills to extend their capabilities beyond parametric knowl- edge. However, retrieving the app
arXiv:2608.07932v1 Announce Type: new Abstract: Sports video analysis is crucial for athletic analytics and broadcasting enhancement. Dense sports video reasoning, however, demands a fine-grained unde
arXiv:2608.00417v2 Announce Type: replace Abstract: Although large language models (LLMs) can produce fluent spatial reasoning traces, their intermediate relations may fail to support the final conclu