Knowledge catalogue
arXiv:2608.30785v1 Announce Type: new Abstract: Production agent skills are directory bundles, not isolated prompts. The root is loaded at activation; references, schemas, scripts, assets, and nested
arXiv:2602.11166v2 Announce Type: replace-cross Abstract: Parameter-efficient fine-tuning (PEFT) methods are widely used to adapt large language models (LLMs) to downstream tasks and are often assumed
arXiv:2608.30214v1 Announce Type: new Abstract: Scientific reasoning remains challenging for open-source models, largely due to the lack of high-quality scientific reasoning data. Existing datasets ar
arXiv:2608.29362v1 Announce Type: cross Abstract: Sparse computations are fundamental to scientific computing, graph analytics, and machine learning, yet their performance is highly sensitive to the d
arXiv:2608.28593v1 Announce Type: new Abstract: With the increasing development of AI regulatory frameworks, ensuring that artificial intelligence systems, particularly generative models, operate in a
arXiv:2608.28907v1 Announce Type: cross Abstract: Task handover requires communicating enough current state for a successor to resume work, yet the relevant information is often divided between system
arXiv:2608.29310v1 Announce Type: cross Abstract: Organizations often develop and maintain portfolios of related applications: independently deployable codebases that share substantial domain logic, i
arXiv:2608.29706v1 Announce Type: new Abstract: A token's representation is carried through the network layer by layer. The whole vocabulary carried together forms a flow. We fit this flow's equation
arXiv:2608.30748v1 Announce Type: cross Abstract: Existing jailbreak evaluations typically characterize robustness using a single attack success rate (ASR) measured in a default configuration (the van
arXiv:2608.28859v1 Announce Type: cross Abstract: Reasoning models do not stop when they know the answer. On DeepSeek-R1-Distill-Qwen-7B the chain of thought runs about twice as long as the model's ow
arXiv:2608.28597v1 Announce Type: new Abstract: Online surveys are a foundational data collection instrument in a variety of fields, with attention checks serving as critical guardians of response qua
arXiv:2608.30842v1 Announce Type: new Abstract: Humans play a vital role at every stage of AI development, from data collection and curation to model development and evaluation. However, humans often
arXiv:2608.29016v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated considerable promise in program generation for small-scale and conventional application development; howe
arXiv:2608.29860v1 Announce Type: new Abstract: Uncertainty estimation provides promising capabilities for reinforcement learning (RL) agents. Notably, estimating uncertainty can reduce the training t
arXiv:2604.03592v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models exhibit striking performance disparities across languages, yet the internal mechanisms driving these gaps rema
arXiv:2608.28932v1 Announce Type: new Abstract: Voice products increasingly need affective cues that are present in speech but absent from transcripts. We introduce VocalAffectBench, a public, test-on
arXiv:2608.19269v4 Announce Type: replace-cross Abstract: Benchmarks can run without determining what their results license. We freeze a large evaluation collection and attempt to replay its historica
arXiv:2608.30647v1 Announce Type: new Abstract: Language models can answer from precomputed memory, a model's saved reading of a body of material, reused across requests instead of read again at each.
arXiv:2608.31059v1 Announce Type: cross Abstract: When do text embeddings work as inputs to empirical analysis? Their use rests on an assumption: that we can trade text for its low-dimensional embeddi
arXiv:2608.29897v1 Announce Type: new Abstract: Long-horizon agents need a context manager to compress growing interaction histories into a bounded working context, via passive strategies or active st
arXiv:2608.29834v1 Announce Type: new Abstract: Collaborative conversations frequently contain references whose targets are indirect rather than named: resolving 'this looks like the fix discussed yes
arXiv:2608.28407v1 Announce Type: new Abstract: Multi-trait Automated Essay Scoring (AES) requires rubric-grounded reasoning across interdependent traits, rather than isolated score prediction. Existi
arXiv:2608.28312v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) can memorize identity-specific facts about people in their fine-tuning data, creating privacy risks when a pe
arXiv:2405.20971v3 Announce Type: replace-cross Abstract: Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors in
arXiv:2608.28541v1 Announce Type: new Abstract: A code world model accepted by a sampling gate can be exactly right on everything the gate can see and arbitrarily wrong beyond it. We characterize what
arXiv:2608.28455v1 Announce Type: new Abstract: Contrastive vision-language learning uses paired chest CT volumes and radiology reports to learn abnormality classifiers without manually annotated labe
arXiv:2608.28432v1 Announce Type: new Abstract: Recent advances in in-context learning (ICL) text-to-SQL have substantially improved execution accuracy on public benchmarks by assembling increasingly
arXiv:2601.17658v2 Announce Type: replace Abstract: Large-scale computational research on conspiracy theories has focused exclusively on believers' online behavior, leaving the harm experienced by tho
I've made a modification of llama.cpp MTP for people that want to run models like QWEN 27B on 16GB and similar setup, the focus is reducing the memory cost of MTP allowing more speed for less ctx cost
arXiv:2608.28476v1 Announce Type: new Abstract: Long-horizon agentic tasks require large language models (LLMs) to iteratively retrieve, integrate, and maintain dispersed information across multi-turn
arXiv:2608.27808v1 Announce Type: cross Abstract: Self-report is the cheapest oversight channel a deployer has, and on capable computer-use agents (CUAs) it fails precisely where oversight matters. On
arXiv:2608.28283v1 Announce Type: new Abstract: In computational argumentation, obtaining arguments that explicitly support or attack given claims is a critical precursor to downstream reasoning tasks
arXiv:2608.27856v1 Announce Type: new Abstract: Recent advances in large language models are enabling autonomous clinical agents to perform increasingly complex electronic health record (EHR) modeling
arXiv:2608.28155v1 Announce Type: new Abstract: Professional financial examinations require models to combine domain knowledge, calculation, and judgment, yet no benchmark covers the full CFA and FRM
arXiv:2608.27672v1 Announce Type: new Abstract: We present Qwen-GuidePlay-2B, a 2B-parameter language model for dialogue-game interaction. We fine-tune Qwen3.5-2B using three steps: a) SFT on only suc
arXiv:2608.28154v1 Announce Type: new Abstract: People naturally chat while collaborating and share personal information (i.e., self-disclose) to build rapport and maintain social connections. As robo
Data pipelines are the backbone of the modern enterprise, yet a barrier to entry exists for orchestrating them, making this critical capability unavailable to many data professionals. Following our an
arXiv:2608.27531v1 Announce Type: cross Abstract: The safety of large vision-language models is increasingly stress-tested by multimodal jailbreaks, yet existing attacks remain largely static at the m
Great paper from Google and colleagues. It proposes an interesting approach to improve agents on long-horizon tasks. Long-running agents slow down and start poisoning their own context. Both symptoms
arXiv:2608.28158v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) often produces irregular rollout trees with shared histories. Training root-to-leaf trajectories independently recom
TL;DR: this paper proposes a method to fix hallucination rates to very low levels or zero by disabling neurons which contribute to hallucination. This discovery has been out for a while now, but it ha
arXiv:2608.28435v1 Announce Type: new Abstract: Many robotic tasks are temporally extended and demand precise specifications of subgoals, constraints, and their temporal ordering. Yet human operators
arXiv:2406.10221v3 Announce Type: replace-cross Abstract: Recent developments in vision-language models have significantly advanced video understanding. Existing datasets and tasks, however, have nota
arXiv:2608.28437v1 Announce Type: cross Abstract: Cloud robotics relies on the timely uplink of high-volume sensing streams, yet dynamic environments continually shift the feasible combinations of tra
arXiv:2608.28151v1 Announce Type: new Abstract: A byte-level BPE tokenizer is an ordered list of merge rules, so applying only a prefix yields a vocabulary whose token identifiers are the first rows o
arXiv:2608.28075v1 Announce Type: new Abstract: Manipulation in partially observable environments requires planning under incomplete scene information. In such settings, an initially valid plan may ex
arXiv:2608.27831v1 Announce Type: cross Abstract: Coding agents are now commonly evaluated on the SWE-bench family of benchmarks, whose tasks are built from curated GitHub issues--long, structured, an
arXiv:2608.27471v1 Announce Type: cross Abstract: Fallacies are arguments that employ invalid reasoning, making their automatic detection critical in sensitive contexts such as high-stakes political d
→ rollout throughput: generation speed and GPU utilization → weight sync: fresh weights on the rollout deployment every step → correctness: trainer and inference engine agreeing on the same model Cofo
arXiv:2608.27462v1 Announce Type: new Abstract: Unlike explicit attacks with obvious profanity, implicit hate speech hides malice within seemingly compliant expressions through metaphors and contextua
arXiv:2608.28018v1 Announce Type: new Abstract: Knowledge-intensive reasoning requires Large Language Models (LLMs) to ground answers in provided evidence. When evidence is insufficient, it is desirab
I used Claude Code to help write this pipeline - Gemma4 to turn an idea into a short story, then IndexTTS 2.5 running on an NVIDIA 3080 to use voices from LibreVox and VTCK voices to pin as character
arXiv:2608.28010v1 Announce Type: new Abstract: Flow matching enables likelihood-free training, yet alignment methods increasingly reuse conditional flow matching (CFM) losses as endpoint negative log
arXiv:2608.27518v1 Announce Type: new Abstract: Continual learning (CL) and model merging (MM) both aim to obtain a single model that performs well across multiple tasks, challenged respectively by ca
arXiv:2608.27481v1 Announce Type: new Abstract: Knowledge-intensive multi-hop question answering requires systems to select evidence and compose dependent facts, yet multilingual benchmarks usually tr
I’ve been experimenting with MiniMax H3 and finally have video generation working in TensorSharp. TensorSharp started primarily as a local GGUF/LLM inference engine, so getting a video-generation pipe
i see a lot of posts about the openai <> hugging face incident and i think most of them miss one important element: this attack could have been avoided by simply doing CoT or network monitoring, which
Finally, a paper testing whether hiding your agent skill files actually protects them. The short answer is no. That's concerning. Worth reading if you sell access to a skill or share one across teams.
arXiv:2601.03605v2 Announce Type: replace Abstract: Despite the significant advancements of Large Language Models (LLMs), their factuality remains a critical challenge, creating a growing need for mor
arXiv:2608.26193v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) achieve strong performance on VQA and scene understanding, yet affective reasoning remains vulnerable to shortc