Search: “open-weights”

arXiv:2605.18109v1 Announce Type: new Abstract: In real home deployments, household agents must often operate from a complete household scene and a situated household request, rather than from a clean

arXiv:2605.12772v1 Announce Type: new Abstract: Wu et al. (2026) showed that most frontier large language models (LLMs) recommend a sponsored, roughly twice-as-expensive flight when their system promp

arXiv:2605.12271v1 Announce Type: new Abstract: Humans often specify and create through visual artifacts: typography sheets, sketches, reference images, and annotated scenes. Yet modern visual generat

arXiv:2412.14461v4 Announce Type: replace Abstract: Unstructured text data annotation is foundational to management research. LLMs offer a cost-effective and scalable alternative to human annotation,

arXiv:2605.09268v1 Announce Type: cross Abstract: Users interacting with Large Language Models (LLMs) in a multi-turn conversation routinely refine their requests or pivot to new topics. LLMs, however

arXiv:2602.22953v2 Announce Type: replace Abstract: General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measur

arXiv:2605.10032v1 Announce Type: new Abstract: Cell-type-specific marker genes are fundamental to plant biology, yet existing resources primarily rely on curated databases or high-throughput studies

arXiv:2605.08366v1 Announce Type: new Abstract: We introduce SWE Atlas, a benchmark suite for coding agents spanning three professional software engineering workflows: Codebase Q&A (124 tasks), Test W

arXiv:2605.07823v1 Announce Type: new Abstract: Online group chats are social spaces with implicit behavior patterns that, when broken, are often met with social sanctioning from the group. The abilit

arXiv:2605.04208v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated impressive multilingual capabilities for well-resourced languages, yet their performance on low-resource

arXiv:2605.02881v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models aim to provide a single generalist controller for robots, but today's systems fall short on the criteria that matter

arXiv:2504.20605v2 Announce Type: replace Abstract: Moral stories are a time-tested vehicle for transmitting values, yet modern NLP lacks a large, structured corpus that couples coherent narratives wi

arXiv:2602.04212v2 Announce Type: replace Abstract: Though large language models (LLMs) have enabled great success across a wide variety of tasks, they still appear to fall short of one of the loftier

arXiv:2605.00206v1 Announce Type: cross Abstract: Current transformers discard their rich latent residual stream between positions, reconstructing latent reasoning context at each new position and lea

arXiv:2604.26577v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly considered for deployment as the control component of robotic health attendants, yet their safety in this

arXiv:2604.24827v1 Announce Type: new Abstract: Closed-source frontier labs do not disclose parameter counts, and the standard alternative -- inference economics -- carries 2imes+ uncertainty from har

arXiv:2604.25884v1 Announce Type: cross Abstract: Quantum computing calibration depends on interpreting experimental data, and calibration plots provide the most universal human-readable representatio

arXiv:2509.17314v3 Announce Type: replace-cross Abstract: Software increasingly relies on the emergent capabilities of Large Language Models (LLMs), from natural language understanding to program anal

arXiv:2604.22601v1 Announce Type: cross Abstract: Large Language Models (LLMs) show promise in automated software engineering, yet their guarantee of correctness is frequently undermined by erroneous

arXiv:2604.20273v1 Announce Type: new Abstract: We present ActuBench, a multi-agent LLM pipeline for the automated generation and evaluation of advanced actuarial assessment items aligned with the Int

arXiv:2601.09373v2 Announce Type: replace Abstract: Do Large Language Models (LLMs) genuinely grasp the compositional semantics of events, or do they rely on surface-level probabilistic heuristics? We

Props to @augmentcode for being one of the first to ship Kimi K2.6 to their users. Open models are now the frontier. Support for Kimi K2.6 is now here in Augment Code! We teamed up with @Kimi_Moonshot

I've been a K2.5 superfan since it came out. These new numbers for the next version look incredible. You gotta love competition! Meet Kimi K2.6: Advancing Open-Source Coding 🔹Open-source SOTA on HLE w

arXiv:2604.14171v1 Announce Type: new Abstract: Romanized Nepali, the Nepali language written in the Latin alphabet, is the dominant medium for informal digital communication in Nepal, yet it remains

arXiv:2601.06536v2 Announce Type: replace Abstract: We present Exposia, the first public dataset that connects writing and feedback in higher education, enabling research on educationally grounded com

Reuters: AWS launches Amazon Bio Discovery, an AI-powered application designed to speed up drug development, giving scientists access to biological foundation models — Amazon's (AMZN.O) cloud unit on

arXiv:2604.10825v1 Announce Type: new Abstract: We introduce CheeseBench, a benchmark that evaluates large language models (LLMs) on nine classical behavioral neuroscience paradigms (Morris water maze

arXiv:2604.09024v1 Announce Type: cross Abstract: Multi-modal large language models (MLLMs) have emerged as powerful tools for analyzing Internet-scale image data, offering significant benefits but al

INCREDIBLE GLM-5.1 weights are now opensource > i’ve had early access to the weights for the past few days > and yeah… this one matters a lot benchmarks? > SWE-Bench Pro: 58.4 > beats Opus 4.6 (57.3)

Hey y'all, just following up on my PR to get the new vision tower for 1017 working in ds4 with the quant I promised (the language model loads already, but vision needed my PR). I built to the exact sa

arXiv:2610.21270v1 Announce Type: new Abstract: Trustworthy biomedical AI requires reliable action selection when evidence is missing, stale, conflicting, or late, not only accurate answers on static

arXiv:2610.22067v1 Announce Type: new Abstract: Long-context language models support ever longer context windows, and evaluations typically treat context length as the main indicator of difficulty. Ho

arXiv:2610.22127v1 Announce Type: cross Abstract: Personalization of Large Language Models (LLMs) is increasingly important for user-centric applications, yet prior methods mainly adapt dense LLMs, wh

arXiv:2610.21483v1 Announce Type: new Abstract: Large language models can produce fluent answers that the supplied context does not support. A compact frozen proxy model can detect such answers by rea

arXiv:2610.21667v1 Announce Type: new Abstract: As vision-language models (VLMs) transition from frozen-encoder pipelines to native multimodal architectures, the visual channel increasingly serves as

arXiv:2610.21179v1 Announce Type: cross Abstract: Rubrics as Rewards (RaR) extends reinforcement learning to non-verifiable domains by using an LLM judge to score responses against a structured rubric

arXiv:2610.09895v1 Announce Type: cross Abstract: We study a behavioral mechanism for artificial partiality in conversational agents. The paper reports no human-subjects data and makes no claim about

arXiv:2610.21300v1 Announce Type: new Abstract: To show that a medical device complies with regulation, experts judge whether documents and records meet each requirement and record the judgment for ot

arXiv:2610.22314v1 Announce Type: new Abstract: With people increasingly turning to AI chatbots for mental health support, the need to evaluate these tools is becoming more pressing. Recent benchmarks

Muse Spark Open is now live on Wally, day 0 Best US open model thanks to @finkd 370 tok/s, ~2x faster than any provider on OpenRouter. $5 Free on signup. Media 1/ muse spark open is the most capable U

arXiv:2610.22249v1 Announce Type: new Abstract: Recurring expressions in model-written text are often treated as signatures of machine authorship, yet most of them serve legitimate functions. Whether

Beam is an open model built by Reflection. Beam takes text as input and generates text as output. This release includes the instruction-tuned model in BF16, FP8, and NVFP4 numerics. Beam uses a sparse

arXiv:2610.21731v1 Announce Type: cross Abstract: Web search allows LLMs to access up-to-date information, but it remains unclear why they sometimes produce outdated answers even when relevant evidenc

arXiv:2610.21900v1 Announce Type: new Abstract: An agent's memory must remain useful as information changes across conversations. A new fact may replace an earlier value without making that value irre

arXiv:2610.22009v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used to interpret religious, educational, and culturally sensitive visual content, yet their reliability

arXiv:2610.21159v1 Announce Type: new Abstract: On-screen text can describe what a video shows, or it can frame what the video is supposed to mean. Current benchmarks treat both alike, testing whether