Knowledge catalogue
arXiv:2608.29477v1 Announce Type: cross Abstract: Document question-answering systems increasingly answer questions over collections of retrieved documents rather than one clean source, so robustness
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:2608.28697v1 Announce Type: new Abstract: Additive manufacturing (AM) enables compact hydraulic components whose internal fluid channels can follow free-form 3D paths rather than conventionally
arXiv:2608.29186v1 Announce Type: new Abstract: Federated Video Domain Adaptation (FVDA) enables collaborative learning across distributed and non-IID video datasets while preserving privacy, but is u
arXiv:2608.29008v1 Announce Type: new Abstract: Accurate forecasting of grape berry temperature (Tb) is essential for enabling timely heat stress management in vineyards. In this study, a feed-forward
arXiv:2608.28874v1 Announce Type: new Abstract: The automated sorting of shredded black plastics from end-of-life (EOF) industrial waste presents a significant challenge in recycling facilities, prima
arXiv:2608.29601v1 Announce Type: cross Abstract: We present N_0-Foundation, a paradigm for tactile-enabled embodied manipulation, which integrates tactile sensing hardware, large-scale multimodal dat
arXiv:2608.29331v1 Announce Type: new Abstract: Video traffic constitutes a significant share of global web traffic. To reduce its volume, video codecs have been developed and continuously improved. W
I was browsing HF for small LLMs and run into this model. It does not seem to be a fine tune - the model has its own architecture. https://huggingface.co/XHToken/Spark-X2.5-1.7B https://huggingface.co
arXiv:2608.29112v1 Announce Type: new Abstract: Recent advances in anomaly detection (AD) for industrial inspection have pushed performance on standard benchmarks toward saturation. However, strong be
arXiv:2608.29609v1 Announce Type: new Abstract: Semantic segmentation is a crucial task for understanding Mars, the most Earth-like planet in our solar system. However, it is challenging because the M
arXiv:2608.28875v1 Announce Type: cross Abstract: Supplying context at inference time to a large multimodal model is an inexpensive lever for adapting speech transcription to a domain, and earlier res
arXiv:2608.30417v1 Announce Type: new Abstract: We give a complete characterization of equivariant multi-head self-attention (MHSA): if an MHSA layer is equivariant to a symmetry group G, then G can o
arXiv:2608.31036v1 Announce Type: new Abstract: While low-rank adaptation (LoRA) is widely used for parameter-efficient model adaptation, how to regularize its training dynamics for stable and effecti
arXiv:2608.29820v1 Announce Type: new Abstract: Ultrasound B-mode imaging commonly suffers from speckle noise and artifacts, requiring a delicate balance between contrast, resolution, and preservation
arXiv:2608.30678v1 Announce Type: new Abstract: Text-rich image understanding requires multimodal large language models (MLLMs) to organize OCR (Optical Character Recognition)-grounded evidence across
Ollama’s Pro, Max, and Team plans now use transparent per-token pricing. Based on your feedback, every plan includes a monthly pool of usage credits. If you’re on an existing Pro, Max, or Team plan, y
arXiv:2603.23938v2 Announce Type: replace Abstract: Most testbeds for omni-modal models assess multimodal understanding via textual outputs, leaving it unclear whether these models can properly speak
arXiv:2608.30320v1 Announce Type: new Abstract: We describe the architecture and ablations of Qwen3.8-Flash-Next, a sparse mixture-of-experts model with 125B parameters, 6B activated per token, and ad
arXiv:2608.29513v1 Announce Type: cross Abstract: Machine unlearning enables deep neural networks to selectively remove the influence of specific data in response to privacy and regulatory requirement
arXiv:2608.29598v1 Announce Type: new Abstract: We present the first systematic study of the resilience of text-to-video (T2V) diffusion models under random hardware-level faults. While T2V models are
arXiv:2608.31096v1 Announce Type: new Abstract: Class-incremental learning (CIL) requires a model to incrementally learn tasks that contain new classes without accessing earlier training data while pr
arXiv:2608.29420v1 Announce Type: new Abstract: Frontier-model leaderboards now rank systems based on economic benchmarks, tests of how well models carry out professional tasks from software engineeri
arXiv:2608.30952v1 Announce Type: cross Abstract: Chemistry questions often demand exact computation and database lookups that a language model cannot supply from its parameters, so it must reach for
arXiv:2608.31137v1 Announce Type: new Abstract: Ontology alignment (OA) has evolved through several methodological paradigms, ranging from lexical and structural aligners to knowledge graph embedding
arXiv:2608.28663v1 Announce Type: new Abstract: Reliable individual cattle identification supports disease surveillance, vaccination records, breeding management, and livestock insurance. Although the
After an unreleased OpenAI model wreaked enough havoc to make international headlines, OpenAI delayed the development of a different unreleased model suite, Astra, in order to shore up its safety work
arXiv:2506.22343v2 Announce Type: replace-cross Abstract: Text watermarks in large language models (LLMs) are an increasingly important tool for detecting synthetic text and distinguishing human-writt
Orchestra Technologies Ltd., provider of an agentic management service for enterprise data and artificial intelligence, today announced the launch of its platform, giving teams greater control over ho
Our partners @LangChain generate billions of tokens of agent traces a day, their richest signal on how real users react. Judging every one with a frontier closed model like GPT-5.5 or Opus is too cost
Over the summer, we have been sprinting on safety priorities; it's more important than ever for capabilities and safeguards to advance together. We have more to do but have made a lot of progress. We
arXiv:2608.29324v1 Announce Type: new Abstract: Annotation schemas are not neutral. When applied to classical literature, tag sets developed for modern journalistic texts impose source-culture definit
arXiv:2608.30065v1 Announce Type: cross Abstract: Large language models (LLMs) demonstrate strong Helpfulness, Harmlessness, and Honesty (3H) alignment in English-centric settings, but these gains tra
arXiv:2608.28596v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly embedded in scientific workflows for literature analysis, drafting, and review. Existing systems adva
arXiv:2608.30241v1 Announce Type: new Abstract: Recent efforts have aimed to automate scientific diagram generation from paper content (Lin et al., 2026; Zhu et al., 2026a). However, fully satisfying
arXiv:2608.31119v1 Announce Type: new Abstract: Research planning is the decisive capability of AI scientists. Yet a research plan admits no verifiable answer, so reinforcement learning lacks the envi
arXiv:2608.29107v1 Announce Type: new Abstract: While modern generative models excel at modeling complex data, precise inference-time control in conditional generation remains a critical challenge. Cl
arXiv:2507.06415v3 Announce Type: replace Abstract: Long-context reasoning requires accurately identifying relevant information in extensive, noisy input contexts. In this work, we propose PERK (Param
arXiv:2608.28728v1 Announce Type: new Abstract: Urban construction governance requires early decisions that connect workplace safety, permitting requirements, and community impact, yet the relevant ev
arXiv:2608.29819v1 Announce Type: new Abstract: Accurate stereo matching remains challenging in ill-posed regions such as fine structures, reflective, or transparent objects, where appearance cues are
Phonely Ltd. today announced the launch of Alma, a large language artificial intelligence model built for voice agents, trained on more than 10 million real phone conversations. The company said many
arXiv:2310.08774v3 Announce Type: replace-cross Abstract: Phylogenetics is a branch of computational biology that studies the evolutionary relationships among biological entities. Its long history and
arXiv:2608.28891v1 Announce Type: new Abstract: Pixel-level cross-view geo-registration aims to align a query image (e.g., drone) to a geo-referenced satellite map so that every query pixel can be map
arXiv:2608.30597v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) simplifies alignment through pairwise comparisons but assumes all observed preferences are reliable. Real data of
arXiv:2608.29426v1 Announce Type: cross Abstract: Reliable semantic representations derived from city-scale 3D models are increasingly important for urban analysis, infrastructure monitoring, autonomo
arXiv:2608.24921v2 Announce Type: replace Abstract: Graph RAG connects facts no single passage states, but implementations pay three times: in infrastructure, keeping vector store, graph database and
arXiv:2608.30865v1 Announce Type: new Abstract: Dakar's residential rental market remains poorly documented despite its economic and social importance: 54.4% of households are renters, compared to 23.
arXiv:2608.20118v1 Announce Type: cross Abstract: The detection of rare disease-associated cell subsets from high-dimensional single-cell measurements is critical for understanding diseases such as le
arXiv:2608.29624v1 Announce Type: new Abstract: Natural Language Processing methods have enabled novel solutions and advances in the field of privacy, particularly in the sub-domain of text-to-text pr
arXiv:2608.28726v1 Announce Type: new Abstract: The remarkable performance of multimodal large language models (MLLMs) comes at the cost of substantial computational overhead, posing significant chall
arXiv:2508.02208v3 Announce Type: replace-cross Abstract: Evaluating the mathematical capability of Large Language Models (LLMs) is a critical yet challenging frontier. Existing benchmarks fall short,
arXiv:2608.25631v1 Announce Type: cross Abstract: Continuous-time Markov chains (CTMCs) provide the backbone for modeling discrete stochastic dynamics across applied, physical, and biological sciences
arXiv:2608.30564v1 Announce Type: cross Abstract: Mixed-precision quantization (MPQ) assigns a different bitwidth to each linear layer of a large language model (LLM) to minimize the quantization-indu
arXiv:2608.29253v1 Announce Type: cross Abstract: Instance segmentation of overlapping cells in microscopy remains challenging due to semi-transparent structures that produce weak boundaries and mixed
Qdrant has released **Qdrant‑Fineweb‑10B**, a public benchmark dataset comprising dense and sparse embeddings for 10 billion documents from the FineWeb corpus and exact results for 120,000 queries to
arXiv:2608.30229v1 Announce Type: new Abstract: Korean introduces an additional typographical perturbation level not captured by ordinary character-level edit models: because syllable blocks are inter
I only started using some vLLM forks recently in a 4 x 48GB 4090 system. DS4F - ~5000pp/180tg (DSpark) Qwen3.8 Flash next - ~7500pp/135tg (MTP) This is amazing, like having the API in my house. But it
I am absolutely blown away. Yes my setup is crap but the fact that it managed to do this in a single take is unbelievable (and I'm a developer). Hardware used: - Windows PC with 4070ti (12GB VRAM, 32G
if you are on Qwen Flash Next make sure to update your build often https://preview.redd.it/zoq3j9gnjvmh1.jpg?width=900&format=pjpg&auto=webp&s=bb21bc405696df94fd5ce38c22f4ca6dc596135f merged already (
arXiv:2608.30896v1 Announce Type: new Abstract: Automotive mmWave radar can develop vibration, antenna misalignment, radome blockage, and receive-channel degradation that corrupt the signal before per