How Much Do Legal RAG Systems Still Hallucinate?
arXiv:2608.14210v1 Announce Type: cross Abstract: Hallucination is a major challenge for retrieval-augmented generation (RAG) systems in the legal domain, where ungrounded answers can lead to serious
Knowledge catalogue
arXiv:2608.14210v1 Announce Type: cross Abstract: Hallucination is a major challenge for retrieval-augmented generation (RAG) systems in the legal domain, where ungrounded answers can lead to serious
Original Article - https://x.com/p_nawrot/status/2089315591010079034 I've spent the last few years working on efficient attention and KV Cache Compression. I've read many papers, dug deep into referen
arXiv:2608.13914v1 Announce Type: cross Abstract: Electrocardiogram (ECG) recordings are sensitive biomedical data, limiting the ability of hospitals and wearable devices to share raw signals for cent
I created 3 SVG prompts, each one rather hard. Perspective: A animated drone view perspective on a park. Beauty: A beach scene with an evil cat Composition: An AGI breaking out of a virtual sandbox pr
I'm back. Yesterday I released the first version of hyper-optimized Qwen3.8-27B inference engine for a RTX 3090, reaching 82 tps on single request and 672 peak. Over the last 24 hours I've been explor
arXiv:2608.14004v1 Announce Type: new Abstract: In-context learning is commonly formalized as inference from examples of a function. Partial orders instead combine transitivity, antisymmetry, and inco
IIRC, this is the 3rd month in a row that @FireworksAI_HQ is being featured on @tryramp's top software vendor list. This isn't just for inference / model serving (of which we serve 40T+ tokens a day),
arXiv:2608.13958v1 Announce Type: new Abstract: How do we govern AI systems whose reasoning we cannot fully inspect? Governance does not require understanding a system's reasoning. It requires stating
arXiv:2512.14338v4 Announce Type: replace Abstract: Many learning problems are organized by group symmetries. While invariance is often imposed through architectures or group averaging, we ask when it
arXiv:2608.13564v1 Announce Type: new Abstract: Evaluating language-model agents at scale increasingly relies on a second language model as an automatic judge, because the gold signal, an executable e
arXiv:2608.14457v1 Announce Type: new Abstract: The majority of work on summarization evaluation focuses on general summary quality (e.g., ROUGE, BERTScore) or specific desired properties (e.g., reada
arXiv:2608.14070v1 Announce Type: new Abstract: Video virtual try-on is a highly constrained editing task requiring the precise replacement of a target person's clothing while strictly preserving the
arXiv:2608.14317v1 Announce Type: cross Abstract: This research developed a neural network-based model to extract various information from 2D floor plans. We detect lighting symbols, identify the appr
arXiv:2608.13575v1 Announce Type: cross Abstract: Recent machine learning (ML) advances have demonstrated that deep learning (DL) achieves impressive results in different application domains, includin
arXiv:2608.14290v1 Announce Type: new Abstract: We introduce Mobius-v0, an architecture that comprises a globally shared Memory (FFN) that stores knowledge vectors and multiple Reasoners (Self-Attn) t
arXiv:2204.13805v5 Announce Type: replace-cross Abstract: Gender gaps in how scientific work is evaluated are well documented, but their sources remain debated. We ask whether an overlooked factor---t
arXiv:2608.14394v1 Announce Type: new Abstract: Perception is a fundamental component of autonomous driving systems. While LiDAR-based methods have achieved remarkable progress in object detection, th
arXiv:2608.13588v1 Announce Type: cross Abstract: Multi-hop question answering requires complex reasoning across multiple evidence segments, which often overwhelms retrieval-augmented generation syste
Its interesting to see the experiments on how to give AI a computer: Codex & Claude Code use your local machine, ChatGPT Work on the web (as well as Claude and ChatGPT) give the AI a one-time machine
arXiv:2608.13580v1 Announce Type: cross Abstract: Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric la
Join us for a fun night this Thursday (August 20th) in San Francisco! RSVP link below! 👇 This Thursday, August 20th, we’re bringing together four leaders at the forefront of open models, coding agents
arXiv:2608.13863v1 Announce Type: new Abstract: Deep neural network (DNN) inference on mobile devices often incurs high latency and energy consumption due to limited computing and memory resources. To
arXiv:2608.14425v1 Announce Type: new Abstract: LLM evaluations often use fixed sampling budgets, testing every item the same number of times even after estimates are precise. We introduce optstop, a
arXiv:2608.13878v1 Announce Type: new Abstract: In mixed traffic, decision-making for autonomous vehicles (AVs) confronts three interrelated challenges. First, physics-based priors incorporated into r
arXiv:2608.13769v1 Announce Type: new Abstract: Land classification from satellite imagery is important for land management, environmental monitoring, and urban planning. Machine learning methods such
arXiv:2608.14191v1 Announce Type: cross Abstract: The key-value (KV) cache stores information from past tokens and is a major memory bottleneck in long-context inference. Existing quantization methods
arXiv:2608.13562v1 Announce Type: new Abstract: Modern operational systems face uncertainty even in routine conditions, where rare, bursty, and self-exciting events emerge from both exogenous covariat
arXiv:2608.13807v1 Announce Type: cross Abstract: Peripheral nerves buried beneath intact tissue are difficult to visualize during surgery and remain inaccessible to white light wide-field imaging and
arXiv:2608.13695v1 Announce Type: cross Abstract: Large language model providers routinely cite multilingual safety benchmarks spanning a dozen or more languages as evidence that their models are safe
Last week, hundreds of founders and builders gathered for AGENT NIGHT. If you weren't there, here's what you missed including the preview launch of WorkOS Airlock: 01:25 Why agents need a new access c
arXiv:2602.12314v2 Announce Type: replace-cross Abstract: We present LatentAM, an online 3D Gaussian Splatting (3DGS) mapping framework that builds scalable latent feature maps from streaming RGB-D ob
arXiv:2608.14150v1 Announce Type: new Abstract: The second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge evaluates two tasks over complete, unsegmented multilingual conversatio
arXiv:2602.11903v3 Announce Type: replace-cross Abstract: No-reference video quality assessment (NR-VQA) for gaming videos is challenging due to limited human-rated datasets and unique content charact
arXiv:2608.13684v1 Announce Type: new Abstract: This paper describes a neurosymbolic architecture for learning to assemble novel structures using evidence from embodied conversations and task demonstr
arXiv:2608.14281v1 Announce Type: new Abstract: Forecasting crop growth across agricultural landscapes is important for improving the productivity, resilience, and operational management of farming sy
arXiv:2604.06452v2 Announce Type: replace Abstract: When a colleague starts explaining something you already understand, you interrupt them. This simple act, a listener taking control of the conversat
arXiv:2608.14114v1 Announce Type: new Abstract: As the integration of volatile renewable energy sources increases the strain on modern power grids, the use of Reinforcement Learning (RL) for autonomou
arXiv:2608.14511v1 Announce Type: cross Abstract: High-order multiple-input multiple-output (MIMO) detection requires efficient search over a large discrete symbol space while producing reliable soft
arXiv:2608.13629v1 Announce Type: cross Abstract: Clinically actionable, patient-specific hemodynamic assessment, specifically wall shear stress, vortex structure and pressure distributions, is critic
Letta's agent-memory SDK supports persistent agent memory across managed cloud, self-hosted App Server or local deployment, according to Letta.
arXiv:2402.01826v2 Announce Type: replace-cross Abstract: Current blood pressure (BP) technologies and standards were established decades ago, and these standards are still used worldwide today, often
arXiv:2608.14178v1 Announce Type: new Abstract: Tea is known as an important crop in many parts of South and Southeast Asia, yet the production of tea is still hampered by the multiple diseases that d
arXiv:2608.13729v1 Announce Type: new Abstract: Advances in diffusion-based generative models have motivated the use of synthetic image generation to alleviate data scarcity in vision tasks. While thi
Support for the new ling 3.0 models has been merged into llama.cpp: https://github.com/ggml-org/llama.cpp/pull/26608#event-29549472828 Ling tiny 8b1b - https://huggingface.co/inclusionAI/Ling-3.0-tiny
arXiv:2503.01236v3 Announce Type: replace-cross Abstract: This paper addresses fixed-graph terrain-aware path refinement, in which a global planner is restricted to a predefined route space and may re
arXiv:2608.14397v1 Announce Type: new Abstract: Zahavy [2026] argues that Large Language Models, despite their capabilities in induction and deduction, cannot perform the abductive 'Jump' that produce
In medium reasoning mode, it both scores higher than the 3.6 version, AND is very much more efficient (almost half requests needed, and a third less tokens generated) - at DeepSeek v4 Flash 3107 MXFP4
arXiv:2608.14361v1 Announce Type: new Abstract: Intrinsic dimensionality (ID) is widely used to probe the representational complexity of language models, but it remains unclear whether ID differences
arXiv:2309.02007v3 Announce Type: replace-cross Abstract: In Mathematical Morphology for grey-level functions, an image is analysed by another image named the structuring function. This structuring fu
Hi all! I finally just got around to testing out Qwen 3.8 27b. I'm using Unsloth's UD-Q8_K_XL quant as a sit-in replacement to Qwen 3.6 27b, same quant size. Wow -- this thing isn't messing around. I
arXiv:2510.25577v2 Announce Type: replace-cross Abstract: Recent advances in Speech Foundation Models (SFMs) enable direct processing of raw audio, allowing models to respond to subtle paralinguistic
arXiv:2608.14472v1 Announce Type: cross Abstract: Neural Architecture Search (NAS) aims to automate neural network architecture design, reducing reliance on human expertise. Among the various NAS meth
arXiv:2608.14068v1 Announce Type: cross Abstract: Conversational recommendation for e-commerce is increasingly mediated by large language models (LLMs), yet many real-world deployments operate under a
arXiv:2608.14282v1 Announce Type: new Abstract: Monocular temporal 3D detection aims to detect objects in 3D, given a monocular video. Query-based 3D detectors unify detection and cross-view associati
arXiv:2608.14543v1 Announce Type: new Abstract: High-resolution image restoration from degraded inputs is challenging because it must preserve global structural consistency while recovering fine-grain
arXiv:2608.14074v1 Announce Type: new Abstract: AI agents increasingly act on external systems through standardized tool-calling protocols such as the Model Context Protocol (MCP), yet no infrastructu
Many people’s blindness to this problem — AI failing to follow instructions — is like their initially blasé attitude towards hallucinations, with the same fantasy that core, endemic problems would rap
arXiv:2608.14530v1 Announce Type: cross Abstract: Interactive game world models typically autoregress visual observations directly in pixel or latent space, forcing structured properties such as pose,
arXiv:2608.14221v1 Announce Type: new Abstract: Autoformalization is commonly framed as translating natural-language mathematical statements into machine-verifiable formal languages such as Lean 4. Ho
arXiv:2608.13598v1 Announce Type: new Abstract: Agent evaluation relies almost entirely on outcome metrics such as success rate, which capture whether an agent succeeds but not how consistently it beh