Knowledge catalogue
arXiv:2602.13312v2 Announce Type: replace-cross Abstract: As a pioneer of the third-generation photovoltaic revolution, Perovskite Solar Cells (PSCs) are renowned for their superior optoelectronic per
arXiv:2609.03915v1 Announce Type: new Abstract: Question answering agents in long-term conversations must reason over massive, temporally dispersed dialogue histories. However, existing memory mechani
arXiv:2609.03235v1 Announce Type: new Abstract: Large language models (LLMs) face severe memory bottlenecks in long-context inference due to the linearly growing size of key-value (KV) caches. Existin
arXiv:2609.03586v1 Announce Type: new Abstract: Audio-video diffusion models rely on cross-modal attention to coordinate text, sound, and visual content, yet this same mechanism can introduce subtle a
arXiv:2609.03410v1 Announce Type: new Abstract: Idiomatic expressions are an integral part of natural language, reflecting cultural nuances and posing unique challenges for computational models, parti
arXiv:2609.03677v1 Announce Type: cross Abstract: Understanding the composition of large-scale autonomous driving datasets is essential for safety, robustness, and reliable operation across domains. F
arXiv:2609.03949v1 Announce Type: cross Abstract: The problem. A long-lived KV cache must be compressed before the queries that will read it exist; selection by observed attention (H2O, SnapKV) collap
arXiv:2609.01663v1 Announce Type: cross Abstract: Agentic AI systems are increasingly deployed to process sensitive data at inference time, such as healthcare records or financial documents assembled
arXiv:2609.01925v1 Announce Type: cross Abstract: The attention prefilling phase of long-context LLM inference scales quadratically, making self-attention a severe computational bottleneck. Traditiona
arXiv:2606.17350v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have enabled the generation of high-quality prose, yet whether these models are capable of gen
arXiv:2609.02707v1 Announce Type: new Abstract: Does the door-in-the-face technique work on language models? In humans, a large request that is refused makes a smaller follow-up request more likely to
arXiv:2609.02529v1 Announce Type: cross Abstract: Image enhancement and restoration have become standard back-end operations on short-video and social media platforms to boost UGC visual experience. Y
arXiv:2609.02804v1 Announce Type: cross Abstract: For more than 20 years, the Model-RB benchmark frb100-40 remained an open challenge; since 2014, its public record had stood at 99 of 100 variables. W
TimesFM-3 is the third generation of Google Research's zero-shot forecasting model, and the main change from 2.5 is that it handles multivariate inputs natively instead of being limited to a single se
arXiv:2609.01736v1 Announce Type: cross Abstract: Large language models (LLMs) augmented with external tools have demonstrated remarkable capability in solving complex real-world tasks. However, exist
arXiv:2609.01839v1 Announce Type: cross Abstract: Longitudinal prediction from electronic health records (EHRs) is limited by the sparsity and irregularity in patient trajectories, and knowledge augme
arXiv:2609.02216v1 Announce Type: new Abstract: Inductive knowledge graph completion (IKGC) aims to predict missing links involving entities unseen during training, requiring models to learn transfera
arXiv:2609.01671v1 Announce Type: cross Abstract: Security teams and researchers choose knowledge-graph extraction tooling for threat reports on the strength of published triple-F1 scores, yet those s
arXiv:2609.01886v1 Announce Type: new Abstract: The objective of this paper is to match dictionary sign videos to corresponding signs in continuous signing videos, where a match is defined by the visu
arXiv:2609.02519v1 Announce Type: cross Abstract: Uncertain knowledge graphs (UKGs) extend knowledge graphs by assigning each triple a continuous confidence score. Since most possible triples lack obs
arXiv:2609.02364v1 Announce Type: cross Abstract: Existing Human-Robot Interaction (HRI) literature has focused on identifying and structuring errors, failures, conflicts, and knowledge issues (called
Continual learning isn't some fake term but a real goal and arguably one of the most important open ones in 2026. It roughly means: ‘building systems that keep acquiring useful knowledge or skills aft
arXiv:2607.17952v2 Announce Type: replace Abstract: Climate disclosure classification is a fundamental task for analysing corporate climate disclosures, yet such disclosures appear in many different s
arXiv:2609.01818v1 Announce Type: cross Abstract: The browser has become a first-class database host: applications increasingly want to store, query, and reason over structured data entirely on the cl
// Agent Zero Memory // This work separates three things that agent memory systems usually collapse into one. If you build agents with long-term memory, this memory design is a worth a read. Here is h
arXiv:2609.00482v1 Announce Type: new Abstract: Small leaderboard gaps are often interpreted as evidence that one language model is better than another, but their sign may depend on which benchmark it
arXiv:2602.03708v3 Announce Type: replace Abstract: Large Language Models (LLMs) achieve strong performance across many tasks but suffer from high inference latency due to autoregressive decoding. The
arXiv:2609.00951v1 Announce Type: new Abstract: Collaborative perception shares information among multiple agents to obtain a comprehensive scene representation, enhancing the perceptual capability of
arXiv:2609.00967v1 Announce Type: new Abstract: As large language models increasingly act through external tools, deciding when to call a tool has become a central problem alongside deciding how to us
arXiv:2609.00100v1 Announce Type: new Abstract: Psychometric questionnaires contain rich item-level information, yet it remains unclear whether different representation learning objectives recover the
arXiv:2601.13880v2 Announce Type: replace Abstract: Personalized lifestyle health analysis requires long-horizon, multi-dimensional reasoning over heterogeneous lifestyle signals, and recent advances
arXiv:2609.01182v1 Announce Type: new Abstract: Flagship language models appear saturated on benchmarks like MMLU (Hendrycks et al., 2021), scoring above 90% - yet benchmarks test only what the experi
arXiv:2609.00012v1 Announce Type: new Abstract: Long-horizon tasks remain uncommon in large language model (LLM) evaluation, and for a reason: when each step depends on the last, per-step accuracy tha
arXiv:2609.00865v1 Announce Type: cross Abstract: Production agent harnesses such as Claude Code and Qwen-Agent compress context during rollout, but training under compression creates a conditioning p
arXiv:2603.03517v2 Announce Type: replace-cross Abstract: General-purpose large language models (LLMs) that rely on in-context learning do not reliably deliver the scientific understanding and perform
arXiv:2609.00923v1 Announce Type: new Abstract: While feed-forward 3D reconstruction (3R) offers efficient end-to-end modeling, its application in large-scale UAV mapping is hindered by the prohibitiv
arXiv:2609.00918v1 Announce Type: new Abstract: Large language models are increasingly used as interactive recommender assistants. Their evaluation should therefore go beyond plausible item recommenda
arXiv:2609.00291v1 Announce Type: new Abstract: Streaming video understanding requires answering questions that arrive at arbitrary moments over an unbounded video stream. Existing systems primarily f
arXiv:2609.00411v1 Announce Type: new Abstract: Modern face recognition (FR) owes much of its success to deep neural networks that learn to extract compact identity embeddings from face images. These
arXiv:2609.00858v1 Announce Type: new Abstract: Effective humanitarian response depends on the rapid synthesis of heterogeneous, high-volume information sources - a task that routinely exceeds human a
arXiv:2609.00921v1 Announce Type: new Abstract: Personalized Large Language Models (PLLMs) aim to tailor responses to individual users, where a central challenge is preference reasoning: inferring que
arXiv:2609.01103v1 Announce Type: new Abstract: Reducing the modality gap between image and text representations in CLIP is widely expected to improve cross-modal alignment and downstream performance.
arXiv:2608.30817v1 Announce Type: cross Abstract: Geospatial foundation models have emerged as state-of-the-art methods for downstream Earth observation tasks. However, existing pretraining methodolog
arXiv:2604.01452v2 Announce Type: replace Abstract: Scientific discovery is slowed by fragmented literature that requires excessive human effort to gather, analyze, and understand. AI tools, including
arXiv:2512.07571v3 Announce Type: replace Abstract: This paper presents a simple method that allows to easily enhance textual pre-trained large language models with speech information, when fine-tuned
arXiv:2608.30556v1 Announce Type: new Abstract: Path-finding over knowledge graphs has become an effective way to ground LLM reasoning on multi-hop questions. However, biomedical QA introduces two dis
arXiv:2603.13584v3 Announce Type: replace-cross Abstract: Deep learning has achieved recognition for its impact within natural sciences, yet the prohibitive financial and technical cost of training mo
arXiv:2606.18586v2 Announce Type: replace-cross Abstract: Physical events are not understood by their names alone, but by the causal state changes that compose them. A clip-level label such as 'bounce
arXiv:2608.28625v1 Announce Type: cross Abstract: We study predictive pretraining for scientific document representation using the discourse structure of papers. We propose SciJEPA, a citation-free fr
arXiv:2608.30372v1 Announce Type: new Abstract: As Large Language Models rapidly advance, performance on standard multiple-choice question answering (MCQA) benchmarks is reaching saturation. While the
arXiv:2606.15932v3 Announce Type: replace Abstract: While Large Language Models (LLMs) have substantially advanced text-to-code generation, many real programming tasks specify intent through visual ar
arXiv:2608.30398v1 Announce Type: new Abstract: In pointwise document reranking, Chain-of-Thought models typically underperform direct scoring models. While existing diagnostics attribute this to infe
arXiv:2608.30342v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) enables photorealistic real-time novel view synthesis, yet placing a virtual camera to capture a desired frame remains larg
arXiv:2608.31170v1 Announce Type: new Abstract: While WhisperX accelerates speech transcription via intra-audio batching, it isolates audio segments, losing the historical context needed for coherent
arXiv:2601.05107v2 Announce Type: replace Abstract: As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining styl
arXiv:2608.30023v1 Announce Type: cross Abstract: Generative engines such as ChatGPT, Gemini, and Perplexity answer buyer questions directly and name a shortlist of brands inside the answer. Studying
arXiv:2602.17690v3 Announce Type: replace-cross Abstract: Graphic design generation demands a delicate balance between high visual fidelity and fine-grained structural editability. However, existing a
arXiv:2508.01684v2 Announce Type: replace Abstract: While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains
arXiv:2608.28635v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have advanced document understanding, visual question answering, and text extraction. However, their r
arXiv:2608.30294v1 Announce Type: new Abstract: Streaming video understanding requires answering questions at arbitrary times over a continuously growing visual stream. The central challenge is to com