Knowledge catalogue
arXiv:2608.04003v1 Announce Type: new Abstract: Recursive self-improvement requires agents to turn accumulated experience into better future behavior. Personal AI agents offer a concrete setting for s
arXiv:2608.03691v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are increasingly used to translate webpage screenshots into front-end code, but repeated UI patterns may sway
arXiv:2608.03048v1 Announce Type: cross Abstract: Long-context reasoning remains a critical bottleneck for large language models, as recent recurrent-memory approaches face two inherent challenges: se
arXiv:2608.03579v1 Announce Type: cross Abstract: Modern multi-tenant Low-Rank Adapters (LoRAs) serving systems concurrently host tens to hundreds of LoRA adapters. Though powerful, this introduces a
arXiv:2603.24413v2 Announce Type: replace Abstract: Poetry generation in Sanskrit typically requires the verse to be semantically coherent and adhere to strict prosodic rules. In Sanskrit prosody, eve
arXiv:2608.03041v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) approaches for flexible job shop scheduling (FJSP) heavily rely on attention-centric architectures to achieve state-
arXiv:2608.03612v1 Announce Type: cross Abstract: Virtual contrast enhancement (VCE) synthesizes enhanced breast MR images from pre-contrast acquisitions. Modern latent generators offer strong image p
Prime Agent is an open-source coding and research agent for general and long-running work. A self-improving RLM harness for coding and long-running autonomous tasks. Designed to be both token-efficien
arXiv:2512.01370v2 Announce Type: replace-cross Abstract: Diffusion-based solvers for partial differential equations (PDEs) are often bottle-necked by slow gradient-based test-time optimization routin
arXiv:2608.03294v1 Announce Type: new Abstract: We study the problem of learning multi-head softmax attention from black-box input-output access. The learner may query arbitrary real-valued token sequ
So one of yall mentioned that cuda 13.1 or 13.2 is broken for unsloth so I looked in to it, and they were right. I had 13.2 installed, after I switched to 13.3 no more looping!!! Before the cuda updat
arXiv:2603.09986v3 Announce Type: replace-cross Abstract: Hallucinations, the tendency for large language models to provide responses with factually incorrect and unsupported claims, is a serious prob
arXiv:2608.03854v1 Announce Type: new Abstract: When decoder language models are used as classifiers, predicted class probabilities depend on implementation choices, including the prompt template, ver
arXiv:2608.02980v1 Announce Type: new Abstract: Large Multimodal Models (LMMs) have achieved remarkable success on images and short videos, yet scaling them to long videos remains challenging due to f
Questions & Responses(in BOLD) below. Favorite question(s) moved to end of the thread with combined responses(removed duplicates). Be optimistic folks. I'm sure we're getting other models too apart fr
Qwen-Image-3.0-Pro is live on Qwen Cloud now! Try it out👇 https://www.qwencloud.com/models/qwen-image-3.0-pro?utm_content=g_20000001188 🔔 Qwen-Image-3.0 is now live on Qwen Cloud! Ranked #1 among Chin
People may remember the Qwen3-TTS llama.cpp demo from a few months ago. That PR said it probably wouldn’t be merged because llama.cpp was missing some of the graph and API pieces it needed. A new impl
Qwen3.8-Max hits #2 in Image-to-WebDev Arena! It sees, it builds~😎 Exciting news: Qwen3.8-Max by @Alibaba_Qwen is #2 in Image-to-WebDev Arena! With 1,631 pts, it’s trailing only Claude Opus 5 (Max) by
arXiv:2608.03219v1 Announce Type: new Abstract: Benchmark gains are often treated as evidence of greater LLM capability. Yet the same gain can reflect different changes in model behavior. A model may
arXiv:2608.03135v1 Announce Type: cross Abstract: Text-to-image diffusion models can generate individual concepts well, but they often omit or merge concepts incorrectly with multiple concepts. We tra
arXiv:2608.02636v1 Announce Type: cross Abstract: Self-evolving skill systems promise to improve agents by turning execution feedback into persistent skill updates without changing the underlying mode
arXiv:2608.03512v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance on text-to-knowledge graph generation and related tasks. Nevertheless, it is still unclear
arXiv:2608.03745v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning offers a promising window into model monitoring. However, monitoring relies on faithfulness, i.e., the model output str
arXiv:2608.03341v1 Announce Type: cross Abstract: Large language models (LLMs) have substantially improved code generation, yet achieving strong functional correctness remains difficult, especially fo
arXiv:2608.02948v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD), where a single model acts as both student and teacher with different contexts, has shown promise in verifiable dom
arXiv:2608.02683v1 Announce Type: cross Abstract: Large Language Model (LLM) agents rely on multi-stage agentic workflows, with stages such as memory, planning, and tool execution, to accomplish compl
arXiv:2608.03228v1 Announce Type: new Abstract: Existing low rank KV cache methods preserve either model weights or key variance, neither of which directly reflects the attention scores used during in
As a market leader in enterprise agentic automation and business orchestration, UiPath is helping to pioneer an industry shift toward agentic AI. With it, the company is deploying autonomous agents to
Hey everyone! Scenema Audio is now a native ComfyUI custom node. Same model that powers scenema.ai now quantized so it fits on 8GB VRAM. When we first released it a few months ago as an API and Docker
arXiv:2608.03860v1 Announce Type: cross Abstract: We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19. Rather than pro
arXiv:2608.03327v1 Announce Type: new Abstract: Hybrid computer-use agents can act through screenshots or call text tools. We find that having a tool available does not settle which way the effect goe
arXiv:2608.03298v1 Announce Type: new Abstract: Agentic presentation generation must preserve source content, maintain coherent visual design, render specialized objects, and produce usable artifacts.
arXiv:2608.02672v1 Announce Type: cross Abstract: Cloud misconfiguration remains a leading cause of security incidents, yet whether LLMs and SLMs can generate security-compliant Infrastructure-as-Code
arXiv:2608.03842v1 Announce Type: new Abstract: When a language model fails on surface-perturbed input (typos, OCR noise, homophones), 'which layer is responsible' has three natural operationalization
arXiv:2608.03063v1 Announce Type: new Abstract: Merchant risk control at large payment platforms screens tens of millions of merchants daily, where false positives harm legitimate merchants and false
arXiv:2608.03573v1 Announce Type: new Abstract: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) exhibit fundamentally different behaviors in enhancing multi-task reasoning for large langu
arXiv:2608.03401v1 Announce Type: cross Abstract: Large language models often reason at length before answering, increasing cost and latency. Prompts and trained settings can shorten this reasoning, b
arXiv:2509.25459v2 Announce Type: replace Abstract: Large Language Models (LLMs) show promise in generating long-form scientific explanations that synthesize evidence and connect multiple factors. How
arXiv:2608.02665v1 Announce Type: cross Abstract: A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form. We ask whether that reading is f
SITUATION DETECTED: Prime Intellect is releasing Prime Agent, a self-improving harness for coding and long-running autonomous tasks. The team reports 95.5% on ARC-AGI-3, above the human baseline, and
Skill libraries are shipping in agent harnesses on the assumption that writing skills down compounds. A new benchmark tests that directly. ContinualSkillBench covers five domains, each with 100 interc
arXiv:2608.03580v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have demonstrated remarkable performance in processing and understanding both text and images, their large parameter
arXiv:2608.04009v1 Announce Type: new Abstract: Large language models (LLMs), and the agents built on top of them, are now benchmarked heavily on whether they can finish a task -- fix a bug, drive a b
arXiv:2607.27703v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task
arXiv:2608.02668v1 Announce Type: cross Abstract: Residual connections are the de facto mechanism for training deep neural networks stably. Geodesic Normalization (GeoNorm) recasts them on a Riemannia
Hear me out before you roll your eyes. We tend to only recognize turning points in hindsight. Nobody in 1993 thought the Mosaic browser would be a history book moment, but the web is. I think Stable D
arXiv:2603.29368v2 Announce Type: replace Abstract: Driven by the advancement of 3D devices, stereo vision tasks including stereo matching and stereo conversion have emerged as a critical research fro
arXiv:2511.15339v3 Announce Type: replace-cross Abstract: Automotive telemetry data exhibits slow drifts and fast spikes, often within the same sequence, making reliable anomaly detection challenging.
arXiv:2608.02689v1 Announce Type: new Abstract: We convert 21 of 28 full-attention layers of Qwen3-0.6B-Base into KDA (Kimi Delta Attention) linear-attention layers on a single consumer-grade GPU budg
Hello, I'm the guy who made Sulphur 2. With the recent release of a certain video model, we are looking to mobilize and train Sulphur 3 on this new model. We are targeting $10,000 USD. This certain ne
arXiv:2608.03084v1 Announce Type: new Abstract: End-to-end driving requires a coherent understanding of future scenes, yet existing methods model these scenes using task-specific heads and output form
arXiv:2608.03952v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to provide conversational practice for English-as-a-second-language (ESL) learners. Effective ESL tut
arXiv:2608.03660v1 Announce Type: new Abstract: Reinforcement fine-tuning (RFT) is widely believed to inherently resist catastrophic forgetting in continual post-training of multimodal large language
arXiv:2608.03699v1 Announce Type: new Abstract: Persistent memory helps long-term agents retain knowledge, yet a single update error can repeatedly distort future retrieval and reasoning. Most existin
arXiv:2608.03319v1 Announce Type: cross Abstract: Future integrated sensing and communication (ISAC) architectures separate the sensing entity (SE) that acquires measurements from the sensing function
arXiv:2608.03557v1 Announce Type: new Abstract: Tabular-to-image methods that convert tabular data into visual representations have emerged as a novel paradigm for leveraging the high performance of d
Hello everyone Yesterday I gave a report on Gemini bugs and the techniques I learned on Gemini so far with the Engineering Prompt and interestingly today I got a very interesting and controversial ans
arXiv:2608.03263v1 Announce Type: cross Abstract: We test whether the 'compositional ignition' reported in latent-reasoning models is real computation, an instrument artifact, or inherited from verbal
arXiv:2603.20381v2 Announce Type: replace-cross Abstract: Understanding the fundamental mechanisms governing the production of meaning in the processing of natural language is critical for designing s
So I'm looking at https://huggingface.co/unsloth/DeepSeek-V4-Flash-0731-GGUF and I realize my 128GB of DRAM just isn't cutting it for this (incredibly powerful) model. If only I had another 64GB, I th