Knowledge catalogue
arXiv:2609.02417v1 Announce Type: cross Abstract: Multi-turn agentic RL increasingly treats credit assignment as a targeting problem: given a terminal verifiable reward, per-turn methods localize cred
arXiv:2609.01795v1 Announce Type: new Abstract: Vision-language object detectors (VLODs) achieve strong zero-shot performance but remain vulnerable to distribution shifts during deployment. Mean-teach
arXiv:2609.02797v1 Announce Type: cross Abstract: People increasingly use language models to support life decisions. Many such decisions involve a probabilistic forecast: How likely is a major life ev
arXiv:2609.02068v1 Announce Type: new Abstract: Probabilistic multivariate time series (MTS) forecasting is crucial for modeling complex dynamical systems. However, existing diffusion-based methods re
arXiv:2609.02771v1 Announce Type: cross Abstract: Training data attribution (TDA) aims to identify training examples that shape model behavior, but its intervention value depends on both which example
arXiv:2609.01918v1 Announce Type: new Abstract: Energy poverty is nearly absent from NLP-for-social-good, and the little existing work is either static retrieval/QA or relies on carbon-intensive cloud
arXiv:2609.02219v1 Announce Type: cross Abstract: Autonomous lunar missions require real-time per- ception under three coupled constraints: extreme low-light conditions, limited onboard compute, and r
arXiv:2609.01815v1 Announce Type: new Abstract: How humans grow and maintain abstract knowledge from the sparse, streaming noisy data of experience is a longstanding challenge in cognitive science. An
Krea 2 Turbo — 4-Step Distillation LoRA (work in progress) A LoRA for Krea 2 Turbo that reduces the minimum usable step count from 8 to 4. ⚡ Half the steps — 8 → 4, on Turbo's own deployment sigmas. ⏱
arXiv:2609.02737v1 Announce Type: cross Abstract: Language models spend most of their attention on a small fraction of context, yet they read the entire KV cache to find the few tokens that matter. If
arXiv:2609.02649v1 Announce Type: new Abstract: Aggregating noisy, conflicting textual hypotheses into a reliable consensus is a fundamental challenge when deploying NLP systems in real-world industri
arXiv:2510.10268v3 Announce Type: replace-cross Abstract: In many applications, one must propagate parameter uncertainty from an earlier (upstream) analysis, available as samples, to subsequent (downs
arXiv:2609.02158v1 Announce Type: cross Abstract: Legal Judgment Prediction (LJP) models are typically trained on documents that describe facts from a prosecutorial perspective. Existing datasets furt
arXiv:2609.02566v1 Announce Type: new Abstract: Machine-learnt corrections can complement numerical weather prediction only if they adapt to the evolving model state while preserving dynamical consist
Paper Instruments benchmarked sandbox providers for their RL rollouts, and E2B's tool execution came in up to 3x faster than every other sandbox provider they tested, reducing idle GPU time and traini
arXiv:2609.02108v1 Announce Type: cross Abstract: Diffusion language models (DLMs) have emerged as a promising alternative to the auto-regressive paradigm. With bidirectional attention and any-order g
arXiv:2407.14845v4 Announce Type: replace-cross Abstract: Large language models (LLMs) are widely used in decision-making across diverse domains. Ensuring the generation of safe and reliable responses
arXiv:2609.02242v1 Announce Type: new Abstract: AI assistants often collaborate by proposing candidate edits, plans, or designs that users evaluate before adoption. Existing assistance methods focus o
arXiv:2609.01743v1 Announce Type: new Abstract: Edge vision models are difficult to deploy on resource-constrained hardware, making low-bit post-training quantization (PTQ) attractive. In practice, st
arXiv:2609.02292v1 Announce Type: new Abstract: The rapid proliferation of large language models (LLMs) and the growing diversity of their applications presents a unique optimization opportunity: sele
arXiv:2609.02036v1 Announce Type: new Abstract: Few-step diffusion models substantially compress temporal computation, making the spatial cost of each model evaluation an increasingly dominant source
The Information: Sources: Mira Murati's Thinking Machines Lab is in talks to raise 1B+ at a 40B+ pre-money valuation, lower than the 50B+ valuation it sought last year — Thinking Machines Lab, the AI
arXiv:2609.02504v1 Announce Type: new Abstract: With the recent rapid progress in generative models, image editing has made remarkable advances, yet achieving faithful edits that precisely modify only
Hey everyone, Wanted to share a short paper we just published exploring a simple but surprisingly effective optimization for sparse MoE reasoning models. The problem: MoE reasoning models (especially
arXiv:2609.01738v1 Announce Type: new Abstract: Unexploded ordnance (UXO) continues to restrict civilian access, agricultural activity, infrastructure recovery, and environmental remediation in contam
arXiv:2609.02846v1 Announce Type: new Abstract: Stable 4-bit floating-point (FP4) pretraining is difficult because the E2M1 payload represents only a narrow range of magnitudes. NVIDIA's Transformer E
Bloomberg: Vals analysis: open-weight models performing multi-stage tasks, like building a web app, can have an environmental impact 10K times greater than simple queries — Benchmarker Vals AI finds t
Continual learning isn't some fake term but a real goal and arguably one of the most important open ones in 2026. It roughly means: ‘building systems that keep acquiring useful knowledge or skills aft
arXiv:2609.02438v1 Announce Type: new Abstract: Large language models can look capable of logical reasoning, but correct or incorrect answers alone tell us little about what the model represents inter
arXiv:2609.00591v1 Announce Type: new Abstract: An image may be worth a thousand words, but most captioning models describe it in only a few. Modern vision-language models produce fluent high-level ca
arXiv:2609.00798v1 Announce Type: new Abstract: Pixel-space diffusion has recently emerged as a promising direction for high-fidelity image generation by modeling images directly in the original pixel
There is a video stream running on my desktop right now. It has sound, it has never repeated itself, and it will not stop. I point VLC at a local URL and it plays. One RTX 5090 does all of it — no clo
arXiv:2609.00846v1 Announce Type: new Abstract: The rising prevalence of psychological disorders necessitates effective emotion monitoring, yet current methods relying on facial or physiological signa
arXiv:2607.10628v2 Announce Type: replace-cross Abstract: We present Anamnesis, an interactive system for demographically controllable survey simulation using large language models. Open-source and de
arXiv:2506.19935v2 Announce Type: replace-cross Abstract: Efficiently scaling Large Language Models (LLMs) necessitates exploring alternatives to dominant autoregressive (AR) methods, with Masked Diff
arXiv:2609.01100v1 Announce Type: new Abstract: In current Mixture-of-Experts architectures, routing is performed based on representations dominated by structure shared across all tokens, limiting exp
arXiv:2609.00495v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) generate text through iterative denoising rather than left-to-right decoding. This generation paradigm introdu
arXiv:2609.00891v1 Announce Type: new Abstract: Sharing context between LLMs in a multi-model system requires the receiving model to prefill the shared prefix because KV caches are model-specific. Rec
arXiv:2609.00088v1 Announce Type: cross Abstract: LLM judges, models that score another system's output, can be gamed by the systems they score. Recent work identifies one defence that works: the judg
arXiv:2609.00960v1 Announce Type: new Abstract: Magnetic resonance images of the same subject look markedly different across field strengths, which complicates the comparison and pooling of data acros
arXiv:2609.00804v1 Announce Type: new Abstract: Exploring unknown environments with multiple UAVs requires coordination under intermittent communication, making decentralized operation a baseline assu
arXiv:2609.00576v1 Announce Type: new Abstract: Item-sensitivity, defined as whether a model's choice depends on the specific input rather than on its own output prior, is widely reported as evidence
arXiv:2609.00177v1 Announce Type: cross Abstract: General-purpose NLP embedding models perform well on linguistic tasks, but their ability to capture symbolic ontological structure remains unclear. We
arXiv:2609.00551v1 Announce Type: cross Abstract: Multimodal memory offers a scalable interface for long-video question answering, but existing methods often retrieve captions, frames, transcripts, su
arXiv:2606.17506v2 Announce Type: replace Abstract: Evaluations of social bias in LLMs largely focus on whether models generate or imply biased content. However, as LLMs are increasingly used as judge
arXiv:2609.00051v1 Announce Type: cross Abstract: Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the
arXiv:2609.00762v1 Announce Type: new Abstract: Parameter-efficient fine-tuning is usually framed as a question of how many parameters to update. Under a severe trainable-state budget, however, where
arXiv:2609.00447v1 Announce Type: new Abstract: Accurate 3D abnormality segmentation in chest CT requires dense spatial supervision, but obtaining expert voxel-level labels is costly. Radiology report
arXiv:2609.00908v1 Announce Type: new Abstract: Action chunking is a standard execution strategy in modern Vision-Language-Action (VLA) frameworks, but fixed execution horizons impose a trade-off betw
arXiv:2609.01507v1 Announce Type: cross Abstract: Compressed context is usually carried as human-readable text or as rendered images that must be decoded, even when its consumer is a language model. W
arXiv:2609.00237v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems tackle complex reasoning by orchestrating how multiple agents are configured and how they collabora
This may be somewhat specific to Qwen3.8 27b and the Apple M5 series, perhaps, but enough of us are running this combo that it's worth tossing out there. GGUF models with MTP have been the fastest way
arXiv:2609.00552v1 Announce Type: new Abstract: Existing coded-computing designs do not explicitly exploit the intrinsic structure of the input data. In communication systems, statistical structure an
arXiv:2601.01480v3 Announce Type: replace-cross Abstract: Traffic forecasting systems rely on fixed sensor networks that frequently exhibit contiguous blackouts. Such outages are usually treated as ig
arXiv:2609.00696v1 Announce Type: new Abstract: Graph data across diverse domains can expose valuable relational information to unauthorized representation learning, creating a pressing need for prote
arXiv:2609.00390v1 Announce Type: cross Abstract: Wearable EEG systems may expose sensitive information beyond their intended health function, creating substantial risks to neuroprivacy. In this work,
arXiv:2609.00800v1 Announce Type: cross Abstract: Animation production workflows often involve digital colorization of line art, where small unpainted regions ('gaps') frequently occur and remain an u
arXiv:2609.00656v1 Announce Type: new Abstract: Physically Plausible Video Generation (PPVG) seeks to synthesize videos consistent with physical principles, yet remains challenging due to underspecifi
arXiv:2609.01357v1 Announce Type: cross Abstract: Predicting transcriptional responses to specific perturbations is critical for understanding cellular regulatory mechanisms and accelerating drug disc
arXiv:2609.00579v1 Announce Type: cross Abstract: Large language models (LLMs) have shown proficiency in various software engineering tasks, such as code generation and translation. However, a key lim