Knowledge catalogue
arXiv:2608.05832v1 Announce Type: new Abstract: Large language models (LLMs) excel in structured tasks but struggle with dynamic social interactions, where success requires long-term goal coordination
Hey peeps. I know you're tired of low quants giving hard to believe numbers. I'm quite skeptical too and from what I tried I'm often left with the impression that the claims fall short. So this model
arXiv:2608.05265v1 Announce Type: cross Abstract: Prediction of post-wildfire debris flows is critical for mitigating hazards to communities, infrastructure, and resources during intense rainfall in r
arXiv:2608.05780v1 Announce Type: new Abstract: Recent advancements in MLLM-based long-form video understanding have mitigated inference-time computational cost and limited context lengths by selectin
arXiv:2608.05859v1 Announce Type: cross Abstract: Interpretable classification often requires more than accurate predictions for real-life deployment: models should be transparent about the evidence b
arXiv:2507.13311v2 Announce Type: replace Abstract: Realistic and controllable garment synthesis is essential for fashion e-commerce, yet it demands precise coordination between human pose geometry an
arXiv:2608.05920v1 Announce Type: new Abstract: Recent advances in neural scene representations enable photorealistic novel-view synthesis, yet most methods remain tightly coupled to a single renderin
arXiv:2608.05611v1 Announce Type: new Abstract: Large Language Models (LLMs) can exhibit diverse personas, and activating expert personas has been shown to improve domain expertise and task accuracy.
arXiv:2608.06027v1 Announce Type: cross Abstract: In India, almost every social benefit starts with a form, yet the people who need these benefits most are often unable to read or write. Reaching them
arXiv:2608.05608v1 Announce Type: cross Abstract: Multimodal classification typically assumes all modalities are available, yet real-world inputs are often incomplete. Imputation and dynamic fusion ca
Hey everyone, I just wanted to share my journey here for some motivation. Three years ago, I saw the sudden spike in AI and realized it was the future of tech. My goal at the time was to be an indie g
arXiv:2608.06301v1 Announce Type: new Abstract: As LLMs are increasingly deployed within agentic systems, their capabilities depend not only on the model weights but also on the harness: the prompts,
arXiv:2608.06012v1 Announce Type: new Abstract: Search-agent rewards mix answer quality, citation grounding, tool cost, and anti-hacking terms; a high score therefore need not imply that cited evidenc
arXiv:2608.05557v1 Announce Type: new Abstract: Generating high-quality 3D point clouds requires capturing both global shape topology and local geometric details. Existing flow-based methods rely on c
arXiv:2608.05806v1 Announce Type: cross Abstract: While standard Next-Token Prediction (NTP) lays the foundation of language model pre- training, its teacher-forced training paradigm may not be optima
arXiv:2608.06192v1 Announce Type: new Abstract: Estimating physical pressure from vision is essential for understanding contact-rich hand-object interaction. However, prior vision-based pressure estim
arXiv:2608.05980v1 Announce Type: new Abstract: We investigate whether simple transformations can translate representations across heterogeneous text embedding models. Understanding how independently
arXiv:2608.05454v1 Announce Type: new Abstract: Probabilistic prediction heads in neural networks typically output either a Gaussian mixture or a single conformal region. Neither separates the distinc
arXiv:2602.18831v2 Announce Type: replace Abstract: Synthetic data has emerged as a practical alternative to authentic face datasets for training face recognition (FR) systems, especially as privacy a
arXiv:2608.05738v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have become the dominant recipe for generalist manipulation, yet they are almost universally trained by behavior clo
In this episode of @wandb's Gradient Dissent , @l2k and Fireworks CEO @lqiao discuss why she believes the industry is at a turning point... ... one that calls for more open intelligence, not less. The
arXiv:2608.06037v1 Announce Type: new Abstract: Relational inductive biases are essential for capturing structural dependencies among data. This study investigates a dual-level relational framework fo
arXiv:2608.05674v1 Announce Type: new Abstract: Robot data is scarce, so generalist policies need to learn from heterogeneous sources, including human egocentric video, simulation, and real robots, wh
arXiv:2608.06107v1 Announce Type: new Abstract: Machine learning offers a promising avenue to accelerate physical simulations by replacing computationally expensive traditional Partial Differential Eq
arXiv:2608.05475v1 Announce Type: new Abstract: Task knowledge is commonly stored either as text in the prompt or as an update to model weights. Text is modular but must be interpreted on every use, w
arXiv:2608.06041v1 Announce Type: cross Abstract: Large language models (LLMs) have been shown to exhibit strong Python preferences when generating project-level code, but there is currently no system
arXiv:2608.06060v1 Announce Type: new Abstract: Unified multimodal retrieval aims to identify candidates that satisfy complex user intent expressed through heterogeneous inputs. Although Large Vision-
A fresh llama.cpp PR (#26689) changes what looks like a tiny SYCL FlashAttention dispatch decision. With a quantized KV cache ('q4_0' / 'q8_0'), decode was being sent through the VEC kernel. On the au
arXiv:2604.01280v2 Announce Type: replace-cross Abstract: Knowledge-based Visual Question Answering (KB-VQA) requires Multimodal Large Language Models (MLLMs) to identify and combine fine-grained visu
arXiv:2607.16284v2 Announce Type: replace Abstract: Micro-Actions (MAs) are subtle and spontaneous human behaviors that provide important non-verbal cues in social interaction and affective communicat
arXiv:2608.05872v1 Announce Type: cross Abstract: Standard Large Language Models (LLMs) execute layers sequentially. Dynamic layer routing, i.e. search for a different execution path through layers in
arXiv:2510.03997v2 Announce Type: replace Abstract: Understanding how patients perceive their physicians is essential to improving trust, communication, and satisfaction. Patients increasingly consult
arXiv:2608.05209v1 Announce Type: new Abstract: Constructing reliable online HD maps remains challenging in dynamic urban environments due to moving objects and occlusions. While recent works employ f
arXiv:2608.06257v1 Announce Type: new Abstract: Current video world models struggle in multiplayer environments because they entangle world state with view-dependent visual latents, leading to redunda
arXiv:2608.06253v1 Announce Type: new Abstract: Metabolomics knowledge is distributed across heterogeneous resources and remains difficult to translate into predictive representations. We developed Me
arXiv:2608.05825v1 Announce Type: new Abstract: Human social communication, such as affection and intent, is often conveyed in highly implicit ways, where underlying meanings are expressed through ind
arXiv:2608.06292v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves question answering by grounding large language models (LLMs) in external knowledge such as text corpora. H
arXiv:2608.05773v1 Announce Type: new Abstract: A geometry-conditioned, neuro-symbolic closed-loop architecture is proposed for laser powder bed fusion, in which a standards-aligned ontology operates
arXiv:2608.06296v1 Announce Type: new Abstract: On-policy (Self-)Distillation (OPD / OPSD) has shown strong potential for post-training large language models (LLMs). However, existing methods still re
arXiv:2510.22899v2 Announce Type: replace Abstract: We investigate the role of network architecture in shaping the inductive biases of modern score-based generative models. To this end, we introduce t
arXiv:2608.05707v1 Announce Type: new Abstract: Frame selection is essential for applying Large Multimodal Models (LMMs) to long videos due to severe frame redundancy and limited context windows. Sinc
arXiv:2604.01170v2 Announce Type: replace-cross Abstract: While test-time scaling has enabled large language models to solve highly difficult tasks, state-of-the-art results come at exorbitant compute
arXiv:2608.05843v1 Announce Type: new Abstract: Restoring high-fidelity remote sensing imagery from extreme low-light degradation is indispensable for reliable Earth observation and downstream machine
arXiv:2603.10711v3 Announce Type: replace Abstract: Real-time solution of nonlinear optimal control problems remains challenging on embedded robotic hardware, where conventional solvers often rely on
arXiv:2604.04444v2 Announce Type: replace Abstract: Open-vocabulary object detection (OVOD) enables models to detect any object category, including unseen ones. Benefiting from large-scale pre-trainin
arXiv:2608.05586v1 Announce Type: new Abstract: Autonomous robot navigation requires the rapid generation of obstacle-free regions for trajectory planning. However, existing corridor generators strugg
arXiv:2601.21124v2 Announce Type: replace-cross Abstract: Current multimodal LLMs process audio as a mono stream, ignoring the rich spatial information essential for embodied AI. Existing spatial audi
arXiv:2608.05341v1 Announce Type: new Abstract: Vision-Language Models (VLMs) for radiology report generation are typically trained on retrospective clinical reports, which suffer from omission noise:
arXiv:2608.05666v1 Announce Type: new Abstract: We introduce Potential Matching Optimal Transport (PMOT), a potential-flow framework for general p-cost optimal transport with c_p(x,y)=|x-y|^p. PMOT pa
arXiv:2608.05249v1 Announce Type: cross Abstract: Real-world multimodal instructions often bundle multiple requirements with unequal importance, yet most multimodal training data still reduce instruct
arXiv:2608.05225v1 Announce Type: new Abstract: Research agents can increasingly search literature, propose hypotheses, generate code, run experiments, and draft manuscripts from a single topic. Howev
arXiv:2608.05326v1 Announce Type: cross Abstract: Autoregressive large language model inference is increasingly constrained by the memory footprint of the Key-Value (KV) cache. A dominant line of work
arXiv:2608.05466v1 Announce Type: new Abstract: High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because ea
arXiv:2511.20633v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) policies excel in aligning language, perception, and robot control. However, most VLAs are trained purely by imitation,
arXiv:2608.05651v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long
arXiv:2608.05945v1 Announce Type: new Abstract: Test-time adaptation (TTA) can improve the recognition accuracy of vision-language models under distribution shift, but often degrades calibration, maki
arXiv:2608.06221v1 Announce Type: cross Abstract: Learning from demonstration (LfD) provides a developmental framework through which robots can develop motor skills by observing and imitating human dy
arXiv:2608.05430v1 Announce Type: cross Abstract: The remarkable instruction-following ability of modern LLMs has enabled their practical use as the minds of agents that can autonomously complete incr
arXiv:2608.05903v1 Announce Type: new Abstract: Mainstream World-Action Models (WAMs) adapt pretrained video generation models (VGMs) for robot control, transferring their learned dynamics prior for a
arXiv:2608.06347v1 Announce Type: new Abstract: Multilingual reasoning transfer is crucial for extending reasoning capabilities of large language models (LLMs) beyond high-resource languages. On-polic