Knowledge catalogue
arXiv:2510.08377v4 Announce Type: replace Abstract: Unified multimodal models have shown promising results in multimodal content generation and editing but remain largely limited to the image domain.
arXiv:2607.04674v1 Announce Type: new Abstract: Recovering dynamic environment maps from a single in-the-wild video is crucial for photorealistic rendering, yet remains a challenge. Recent video gener
During a Bloomberg interview, Yann LeCun (@ylecun ) explains why LLMs are limited in terms of real-world intelligence during a Bloomberg interview. 'Language is a very approximate, reduced, quantized,
If there is ANYTHING I have learned in my early Fable 5 testing, it’s that the judgement calls from AI are getting better and better. Not perfect and not (yet?) a substitute for a human’s taste, conte
Come and chat with us in ICML 🥳 Excited to present Temporal Straightening for Latent Planning in the Tuesday morning session #1509. Let’s talk about world models, JEPA and representation learning. Age
Multimodal prompting enhances coding agents by enabling them to process and integrate multiple types of input data—such as text, images, and code snippets—simultaneously, improving their ability to un
arXiv:2607.02255v1 Announce Type: new Abstract: Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see. The simplest contract appends past observations, to
Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and le
arXiv:2607.02329v1 Announce Type: new Abstract: Autonomous-research agents have demonstrated end-to-end LLM automation in machine-learning sandboxes where execution provides calibration. Frontier phys
arXiv:2607.01510v1 Announce Type: new Abstract: AI agents that autonomously execute tool calls on a user's behalf raise pressing questions about permission management: what role could users play, and
arXiv:2504.12317v2 Announce Type: replace Abstract: Scientific language is a central infrastructure of knowledge production, but it remains unclear whether large language models (LLMs) are altering no
arXiv:2607.01844v1 Announce Type: cross Abstract: This paper showcases a memory-efficient training stack for Mixture-of-Experts (MoE) models. It is a training paradigm that combines and specializes va
arXiv:2607.02460v1 Announce Type: cross Abstract: Post-training large language models (LLMs) without real-world interaction feedback or human-labeled supervision remains challenging, particularly in s
arXiv:2607.01792v1 Announce Type: new Abstract: While decoder-only LLMs excel at a vast array of natural language tasks, it suffers from an asymmetric information flow induced by causal attention: lat
arXiv:2607.01034v1 Announce Type: cross Abstract: Large language model (LLM)-based conversational agents (CAs) are now ubiquitous, creating new opportunities for AI-mediated behavior change. Their cap
arXiv:2607.00481v1 Announce Type: cross Abstract: Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs). While prior work has primarily studied attacks and
arXiv:2607.00374v1 Announce Type: cross Abstract: Composed Image Retrieval (CIR) retrieves a target image from a reference image and a textual modification. While supervised CIR relies on costly tripl
arXiv:2607.00654v1 Announce Type: new Abstract: Video anomaly detection (VAD) with multimodal large language models has shown strong potential, yet most existing methods still depend on large-scale an
arXiv:2607.01204v1 Announce Type: new Abstract: We introduce TiRex-2, a recurrent xLSTM-based time series foundation model that generalizes the univariate TiRex to multivariate forecasting with both p
arXiv:2606.30877v1 Announce Type: cross Abstract: Recent literature shows that large language models (LLMs) are useful for general-purpose tasks yet perform poorly on specific domain ones. One reason
arXiv:2606.32016v1 Announce Type: new Abstract: Multimodal graph foundation models aim to learn reusable knowledge from graphs enriched with text, images, attributes, and relational topology, thereby
arXiv:2606.30973v1 Announce Type: new Abstract: Frictive Policy Optimization (FPO; Pustejovsky et al., 2025) treats friction in collaborative dialogue -- misalignment, misunderstanding, repair -- as a
arXiv:2606.31245v1 Announce Type: new Abstract: Surgical vision-language foundation models typically adopt educational materials, such as surgical lecture videos, to transfer surgical knowledge encode
arXiv:2606.31729v1 Announce Type: cross Abstract: Text-to-speech (TTS) evaluation is an open challenge. While the primary target was 'naturalness,' recent fidelity gains shifted focus toward 'appropri
arXiv:2606.31941v1 Announce Type: cross Abstract: Unstructured navigational features, such as irregular planting or discontinuities, remain the primary failure mode for under-canopy agricultural robot
arXiv:2606.31543v1 Announce Type: new Abstract: Large language models can produce fluent, internally coherent reasoning traces for abstract reasoning tasks while still being confidently wrong - making
arXiv:2506.23102v2 Announce Type: replace-cross Abstract: Current CT report generation frameworks predominantly rely on global feature representations, often failing to capture region-specific details
arXiv:2606.31804v1 Announce Type: new Abstract: Accurate energy demand forecasting is essential for the reliable operation and planning of modern sustainable energy systems. Spatial-temporal graph neu
arXiv:2606.31688v1 Announce Type: new Abstract: LiDAR-based 3D semantic occupancy prediction, which aims to provide accurate and comprehensive scene representation, is crucial for autonomous driving s
arXiv:2606.31875v1 Announce Type: new Abstract: Autonomous vehicles (AVs) must navigate not only motion-based hazards but also socially complex situations whose danger is constituted by inter-agent re
arXiv:2606.31645v1 Announce Type: new Abstract: Vision-language models achieve strong general perception but often struggle with the spatial reasoning required for embodied tasks. We present RoboSpati
arXiv:2606.31916v1 Announce Type: new Abstract: Theory of Mind (ToM) benchmarks for Large Language Models (LLMs) typically rely on passive question-answering formats, but the deployment of LLMs in inc
arXiv:2606.28345v1 Announce Type: cross Abstract: LLM-governed social robots increasingly decide who receives real-world assistance first. As prioritization norms vary across cultures by age, status,
arXiv:2606.29184v1 Announce Type: new Abstract: While Low-rank adaptation (LoRA) enables highly efficient fine-tuning by constraining task-specific updates to fixed low-rank subspaces, this rigid desi
arXiv:2606.29134v1 Announce Type: new Abstract: Rapid flood mapping is critical for emergency response, yet optical imagery is often unusable during major flooding and single-temporal SAR is ambiguous
arXiv:2603.19464v2 Announce Type: replace Abstract: Robotic path planning problems are often NP-hard, and practical solutions typically rely on approximation algorithms with provable performance guara
arXiv:2606.30318v1 Announce Type: new Abstract: General-purpose robot policies should be modeled as dynamical systems, yet many VLA and generative imitation policies still rely on present observations
arXiv:2606.28533v1 Announce Type: cross Abstract: Sequence learning has emerged as the promising paradigm in recommendation systems, surpassing traditional Deep Learning Recommendation Models (DLRM) b
arXiv:2606.28361v1 Announce Type: cross Abstract: Multi-step retrieval-augmented generation (RAG) has been widely deployed as LLM-powered web services for complex question answering, where iterative r
arXiv:2606.30189v1 Announce Type: new Abstract: Current multimodal fusion approaches, particularly those based on static Mixture-of-Experts (MoE) architectures, often struggle to provide the adaptive
arXiv:2606.29961v1 Announce Type: cross Abstract: Large Language Model (LLM)-based agents can solve complex procedural tasks by interacting with environments over multiple turns, but this ability typi
arXiv:2606.20092v2 Announce Type: replace Abstract: Memory remains a critical bottleneck for long-horizon robotic manipulation, as standard Vision-Language-Action (VLA) policies often fail when task-r
arXiv:2606.28476v1 Announce Type: new Abstract: High-precision humanoid control is limited by target-domain dynamics mismatch, where the same control objective can induce different realized motions un
arXiv:2606.28813v1 Announce Type: cross Abstract: Human videos are a scalable source of supervision for robot manipulation, as they are abundant and naturally capture rich object interactions. However
arXiv:2606.28395v1 Announce Type: new Abstract: Recent studies have shown that spatial properties of tumors are critical for understanding disease biology and predicting patient outcomes. These spatia
arXiv:2606.29580v1 Announce Type: new Abstract: Maternal and newborn mortality remain among the highest in sub-Saharan Africa, where midwifery care is often delivered by nurses who lack midwifery trai
arXiv:2606.29225v1 Announce Type: new Abstract: LLM agents handle user requests on behalf of organizations through tool calls and must follow the company policies stated in their system prompts. Prior
arXiv:2606.28392v1 Announce Type: cross Abstract: Accurate lesion segmentation in PET/CT is critical for oncology, yet remains challenging because physiologic tracer uptake and artifacts can mimic mal
arXiv:2606.29360v1 Announce Type: new Abstract: High-resolution Diffusion Transformer (DiT) inference contains substantial spatial redundancy, but many spatially adaptive implementations encode region
arXiv:2606.29723v1 Announce Type: cross Abstract: Continuous physical fields represent a large fraction of data under scientific investigation. Their multiscale structures are central to discovery, ye
arXiv:2606.30639v1 Announce Type: new Abstract: World models offer a principled way to equip long-horizon LLM agents with foresight: predictions of action consequences before execution. However, unrel
arXiv:2606.30543v1 Announce Type: cross Abstract: With the proliferation of speech AI agents, understanding emotional entrainment in conversational interaction has become increasingly important. Emoti
arXiv:2606.27619v1 Announce Type: new Abstract: Dyslexic learners increasingly use artificial intelligence (AI) tools to support reading, writing, organisation, and study-related tasks. However, their
arXiv:2606.27550v1 Announce Type: new Abstract: Multi-token prediction has been shown to increase data density during training, improve downstream text-generation quality, and serves as the defacto ap
arXiv:2606.27808v1 Announce Type: new Abstract: A minute lexical variation can reverse the procedural meaning of an instruction even when the rest of the sentence remains unchanged. In automotive main
arXiv:2606.27779v1 Announce Type: new Abstract: Generating lifelike facial animation for dyadic conversations requires reconciling high-level cognitive intent with precise low-level motor reflexes, ye
arXiv:2606.27826v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly deployed as embodied planners in egocentric environments, where task success requires not only
arXiv:2602.01588v3 Announce Type: replace-cross Abstract: Multimodal time series forecasting is crucial in real-world applications, where decisions depend on both numerical data and contextual signals
arXiv:2606.27472v1 Announce Type: cross Abstract: Large language model (LLM) agents operate over long, multi-session interactions in which facts change: a user moves, a price updates, a plan is revise
How to keep AI spend flat while token usage grows exponentially: Not with friction and spend alerts. With better defaults, routing, and caching. Better Defaults (not Usage Caps) – Engineers can choose