Knowledge catalogue
arXiv:2609.39929v1 Announce Type: cross Abstract: Long-context failures of RoPE-based language models can arise from RoPE's intrinsic tradeoff between maintaining stable token preferences and distingu
arXiv:2609.39007v1 Announce Type: cross Abstract: Sessionized interaction histories contain behavioral patterns that can improve sequential recommendation. However, existing models process all session
arXiv:2609.38956v1 Announce Type: new Abstract: Routing signals of modern vision transformers -- expert gates, attention-residual weights and halting scores -- often improve probes that predict whethe
arXiv:2609.35561v2 Announce Type: replace Abstract: Recursive self-improvement (RSI) seeks to enable AI systems to participate in improving their own capabilities. A concrete pathway is autonomous mod
arXiv:2609.39045v1 Announce Type: new Abstract: Recent advances in large language models have made automatic game generation increasingly feasible, yet reliably improving generated games beyond a play
arXiv:2609.39271v1 Announce Type: new Abstract: Manifold-valued data, and consequently the distributions they induce, are prevalent across many domains, ranging from the locations of geospatial events
arXiv:2609.05797v3 Announce Type: replace Abstract: Safety monitors are evaluated by recall on harmful prompts, regardless of whether the target model would answer them. Yet a monitor matters most on
arXiv:2609.39788v1 Announce Type: new Abstract: Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and
arXiv:2609.39635v1 Announce Type: new Abstract: Given a target dataset, such as faces with eyeglasses, and a background dataset, such as faces without, contrastive analysis separates extit{salient} fa
Salesforce Inc. has signed a definitive agreement to acquire artificial intelligence customer research startup Listen Labs Inc., three weeks after reports first surfaced that the two companies were in
arXiv:2609.38786v1 Announce Type: new Abstract: Differentiable learning typically assumes that the scalar objective evaluated in the forward pass and the gradient supplied to the optimizer in the back
arXiv:2609.38545v1 Announce Type: cross Abstract: Machine-learning signals built from financial text treat what institutions say, and what the media repeat, as evidence about value. But whoever shapes
arXiv:2609.40120v1 Announce Type: new Abstract: Motivated by the computational challenges of large-scale Cox regression, we study stochastic minimization of LogSumExp objectives over large sets. Mini-
arXiv:2609.39304v1 Announce Type: cross Abstract: When an off-the-shelf coding agent is used directly as a robot policy, observing a browser-based 3D interface through screenshots and acting by posing
arXiv:2609.38977v1 Announce Type: cross Abstract: Neural surrogates have emerged as fast alternatives to the numerical simulation of three-dimensional turbulence. However, training them at high resolu
arXiv:2609.38705v1 Announce Type: new Abstract: Foundation models for computational pathology are usually evaluated using AUC and accuracy, while calibration is often left untested. This matters becau
arXiv:2609.40316v1 Announce Type: cross Abstract: Looped transformers and Mixture-of-Experts (MoE) offer complementary routes to efficient scaling: recurrence increases computational depth at fixed pa
arXiv:2609.38832v1 Announce Type: new Abstract: Scaling attention parameters can improve language model quality, but retaining full token histories makes additional heads costly at long contexts. Furt
arXiv:2609.40198v1 Announce Type: cross Abstract: Speech-to-speech systems must solve tasks whose requirements emerge across conversational turns. We introduce SpeechConversationBench (SCB), a focused
arXiv:2609.38899v1 Announce Type: cross Abstract: Video Multimodal Large Language Models (Video-MLLMs) support reasoning over video inputs, yet remain vulnerable to jailbreak attacks that elicit polic
arXiv:2609.39140v1 Announce Type: new Abstract: Learning to complete tasks in unfamiliar environments with unknown rules remains a key challenge for LLM agents. Current LLM agents often record their d
arXiv:2609.39088v1 Announce Type: cross Abstract: Long-form live-streaming TTS requires context-dependent prosody and paragraph-level coherence. However, many existing instruction-based TTS systems us
arXiv:2609.38980v1 Announce Type: new Abstract: Radar hardware faults threaten automated perception, motivating accurate, compact diagnosis and understandable maintenance guidance. We introduce SCORE-
arXiv:2609.38847v1 Announce Type: cross Abstract: Rubric-based reinforcement learning (Rubric-RL) trains language models where no verifier exists. A judge checks each criterion of a rubric, and the ve
arXiv:2609.38840v1 Announce Type: cross Abstract: Single-cell RNA-seq representation learning is fundamentally label-free: cell identities, states, and contexts are not fixed training targets, so what
arXiv:2609.39679v1 Announce Type: cross Abstract: Audio deepfake detection (ADD) must remain effective when new spoofing attacks emerge after deployment. Emerging audio language model (ALM)-based ADD
arXiv:2609.35596v2 Announce Type: replace-cross Abstract: Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying their harness, including their cont
arXiv:2609.39847v1 Announce Type: cross Abstract: Audio language models (ALMs) are increasingly used for audio deepfake detection (ADD), yet existing benchmarks assess their verdicts or rationale plau
arXiv:2609.39026v1 Announce Type: new Abstract: Deep Research agents synthesize evidence into cited reports, yet a well-cited report can still reach a misleading conclusion. Citation correctness check
arXiv:2609.38309v1 Announce Type: cross Abstract: The search for physics Beyond the Standard Model (BSM) is generally limited not by the supply of theory descriptions but by the lack of discriminating
arXiv:2609.38606v1 Announce Type: cross Abstract: As vibe coding becomes increasingly capable and widespread, security vulnerabilities in even functionally correct solutions are a growing concern. Whe
arXiv:2609.38477v1 Announce Type: cross Abstract: Large language models (LLMs) incur substantial storage, memory-bandwidth and energy costs, motivating compact weight representations. Existing seed-ba
arXiv:2609.39768v1 Announce Type: cross Abstract: Certifying a deployed neural network raises decision problems that the verification literature has not classified: whether the model carries a backdoo
arXiv:2609.39785v1 Announce Type: new Abstract: The Segment Anything Model (SAM) relies heavily on massive manual annotations, creating a fundamental bottleneck for model scaling. While unsupervised m
arXiv:2609.38757v1 Announce Type: new Abstract: Large language models are increasingly participating in complex real-world tasks in the form of algorithm-design agents, designing and refining algorith
arXiv:2609.38372v1 Announce Type: new Abstract: A harness is the code around a language-model agent that organizes prompts, calls tools, manages context, and controls execution. As models grow stronge
arXiv:2609.39560v1 Announce Type: new Abstract: Sampling several responses and voting over their answers can improve a language model's accuracy, but repeated answers limit the benefit of additional s
arXiv:2609.39568v1 Announce Type: cross Abstract: Large language models (LLMs) may generate unreliable code on corner cases missed by testing, while formal verification can provide machine-checkable g
arXiv:2609.39296v1 Announce Type: new Abstract: Video semantic communication has attracted increasing attention as a promising approach to improving video transmission efficiency. However, most existi
arXiv:2602.13194v3 Announce Type: replace-cross Abstract: Humans and large language models can predict next letter or word from its prior context much better than random guessing, indicating strong re
arXiv:2601.08355v3 Announce Type: replace Abstract: Vision-Language Models (VLMs) are increasingly deployed in autonomous driving and embodied AI systems, where reliable perception is critical for saf
arXiv:2609.39623v1 Announce Type: new Abstract: The proliferation of high-fidelity generative editing models has made it possible to inject violent or sexual content into otherwise ordinary images whi
Financial Times: SemiAnalysis estimates ~90% of Anthropic's business comes from agentic AI, while sources say nearly 25% of its revenue in 2025 came from just two clients — Powerful AI tools burn thro
arXiv:2609.40360v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning capabilities of large language models (LLMs), yet their predictions r
arXiv:2609.38600v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly used in clinical settings, it is critical to evaluate their reliability under realistic variation in cl
RuntimeAI's September 2026 AI Security Report covered 126 incidents across 38 named organizations — 22 critical, 102 high severity. 53 of those incidents had AI either as the attack tool or the target
arXiv:2609.39645v1 Announce Type: cross Abstract: Multi-agent collaboration lets large language models (LLMs) improve question answering through deliberation and feedback. Yet shared discussion couple
arXiv:2511.10661v2 Announce Type: replace Abstract: It is increasingly important to evaluate the characteristics of systems based on large language models (LLMs). Evaluations in this context often rel
With Live Data in Apps in Amazon Quick, AI-built apps query your governed Quick Sight datasets in real time instead of static, build-time snapshots. Each query runs as the person viewing the app, so r
arXiv:2607.10891v2 Announce Type: replace Abstract: Large language models (LLMs) are rapidly shifting toward agents that solve tasks through diverse interfaces, including web and graphical user interf
arXiv:2609.38997v1 Announce Type: new Abstract: Reasoning models often continue generating after their answers have settled. Settle learns when to stop from answer stability in completed traces. It tr
arXiv:2609.38521v1 Announce Type: cross Abstract: We introduce ShamAN-Q, a sub-1-bit post-training quantization method that extends NanoQuant by replacing each its diagonal reconstruction geometry wit
arXiv:2609.39082v1 Announce Type: new Abstract: As new evidence arrives, a sequence model must update what it remembers and how memory influences predictions. While Transformers incur computation and
arXiv:2609.39892v1 Announce Type: new Abstract: Looped Transformers repeatedly apply the same set of Transformer layers, giving them a recurrent architecture for latent computation. Their strong perfo
arXiv:2609.39144v1 Announce Type: new Abstract: We prove a sharp Gaussian approximation for the invariant law of constant-stepsize SGD with bounded additive noise generated by an exogenous uniformly e
arXiv:2609.38880v1 Announce Type: cross Abstract: We study the last iterate of standard tabular temporal-difference (TD) learning from a single trajectory of a finite Markov reward process. For discou
arXiv:2609.39688v1 Announce Type: cross Abstract: Multimodal encoders such as CLIP underlie many downstream systems, but their web-scale training data embed harmful associations that safety alignment
arXiv:2609.38638v1 Announce Type: cross Abstract: Pickup trucks account for 14% of new light-duty vehicles produced in the United States, yet are among the least aerodynamic. Their open cargo bed adds
arXiv:2609.38530v1 Announce Type: new Abstract: Language models increasingly use architectures that vary attention span and positional encoding across layers, such as applying RoPE with sliding-window
arXiv:2609.39818v1 Announce Type: new Abstract: In many high-stakes settings, human decision-makers can acquire support information before making a decision. However, acquiring information is costly,