arXiv:2611.17820v1 Announce Type: new Abstract: Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment trans…
⏱ Độ trễ thật của tab này: trung bình 7.3 giờ sau khi CVE được công bố (n = 5335, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment transfer to multi-agent LLM teams. We focus on two sof…
Controllable real-world video generation models can condition on a rendered graybox proxy video, which fixes layout, motion and camera. Coding agents can build such videos by reconstructing a 4D scene in Blender, yet no benchmark checks both these videos and the long, multi-shot …
arXiv:2611.13020v1 Announce Type: new Abstract: Electronic design automation (EDA) workflows remain highly fragmented, requiring engineers to coordinate heterogeneous representations, specialised software tools, and iterative verification across multiple design stages. Although …
arXiv:2611.10843v1 Announce Type: new Abstract: Agentic AI systems extend large language models with tools, memory, retrieval, browser or computer-use interfaces, code execution, external services, and multi-agent coordination. Although these capabilities enable agents to act be…
arXiv:2611.17793v1 Announce Type: new Abstract: The performance of offline Multi-Agent Reinforcement Learning (MARL) is limited by the quality of the fixed offline dataset, motivating trajectory augmentation. However, augmenting multi-agent trajectories presents a fundamental ch…
Autonomous agents modify prompts, memories, tools, workflows, and policies using interaction histories. Yet a plausible modification is not necessarily suitable for persistent adoption: candidate selection is adaptive, evaluators may be imperfect, and local gains can hide degrada…
arXiv:2611.17338v1 Announce Type: new Abstract: LLM memory systems often delete facts classified as stale. We show that this hard-filtering step can reduce downstream accuracy when resolver errors delete query-critical facts. Across three models, a controlled sensitivity interve…
arXiv:2611.17621v1 Announce Type: new Abstract: Kernel optimization is essential for efficient large language model (LLM) training and inference on Ascend NPUs. Existing Ascend kernel benchmarks primarily focus on kernel generation, with less emphasis on the ability of agents to…
arXiv:2611.17818v1 Announce Type: new Abstract: Jailbreak attacks can circumvent the safety mechanisms of Large Language Models (LLMs) and lead to the generation of harmful or policy-violating content. We first examine eight jailbreak methods against an LLM-based filter and obse…
arXiv:2610.02805v2 Announce Type: replace Abstract: Threshold signature schemes play a vital role in securing digital assets within blockchain and distributed systems. FROST2 stands out as a practical threshold Schnorr signature scheme, noted for its efficiency and compatibility…
Video generation models produce visually realistic videos but still struggle with physical dynamics and causal consistency. Learning from generated videos requires fine-grained physical supervision, yet reliable quality judgments, correction pairs, and controlled variations are d…
Frontier video generation models work in a VAE latent space that compresses video in both space and time. This compression made training tractable, but now limits high-resolution, controllable, and interactive generation -- doubling resolution quadruples token count, conditions a…
arXiv:2611.13942v1 Announce Type: new Abstract: Cyberattacks against power systems increasingly exploit industrial communication and control dependencies arising from distributed energy resources (DER), remote management, and market-based incentives. Progress on intrusion detect…
arXiv:2611.13336v1 Announce Type: cross Abstract: The effectiveness of a self-improving system relies heavily on the quality of its verifier, which judges the outcome of each improvement round. However, the verifiers of most tasks are written by hand, which is expensive and does…
arXiv:2611.11455v1 Announce Type: new Abstract: LLM-based coding agents are widely used to develop critical production software. Even though coding agents are known to occasionally write vulnerable code, there has not been any investigation into how code base vulnerabilities evo…
arXiv:2611.17620v1 Announce Type: new Abstract: High-level behaviors such as sycophancy and hallucination correspond to directions in a model's activation space (Chen et al., 2025). These directions, known as persona vectors, can suppress undesirable traits either at inference t…
arXiv:2611.17681v1 Announce Type: new Abstract: Complete game generation requires agents to coordinate rules, interactions, states, and presentation over a long development process. A single aggregate score obscures which capabilities are implemented and which requirements remai…
arXiv:2611.17377v1 Announce Type: new Abstract: Visual adversarial robustness remains a fundamental security property as vision systems evolve from conventional classifiers to vision-language models (VLMs) and large vision-language models (LVLMs), with visual inputs remaining an…
arXiv:2611.14924v1 Announce Type: new Abstract: Deployment of retrieval-augmented generation (RAG) for Edge-AI is constrained by memory and bandwidth limitations. A standard 7B parameter model consumes 14 GB Video Random Access Memory (VRAM) in half-precision (FP16), precluding …
arXiv:2611.15238v1 Announce Type: new Abstract: Discrete diffusion generation is emerging as a competitive alternative to autoregressive generation by denoising the entire token sequence through iterative refinement. Its global planning and progressive correction capabilities ar…
arXiv:2611.16890v1 Announce Type: new Abstract: Attributing short LLM-generated texts to a specific source remains challenging for existing multi-bit watermarking methods, which often require long generations or costly decoding to recover payloads reliably. We propose a codebook…
arXiv:2611.14061v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems increasingly rely on vector databases containing documents governed by different access-control policies. Recent search-preserving geometric approaches enforce such access control by str…
arXiv:2512.08289v5 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems enhance LLMs with external knowledge but introduce a critical attack surface: corpus poisoning. While recent studies have demonstrated the potential of such attacks, they typically r…
Speculative decoding accelerates generation by letting a lightweight drafter propose tokens for parallel verification by a target model. Diffusion drafters such as DFlash propose an entire token block in a single forward pass, but mainly focus on text-only tasks, leaving multimod…
Direct diffusion modeling of high-dimensional raw video data is challenging, and existing pixel-space methods often rely on specialized architectures. We introduce JVT (Just Video Transformer), a simple large-patch DiT-style Transformer for pixel-space video diffusion, without a …
arXiv:2611.14850v1 Announce Type: new Abstract: Forward-KL language-model distillation normally computes dense teacher and student scores over the full vocabulary at every supervised position, making training and stored teacher targets expensive. We instead distill from the teac…
arXiv:2611.15109v1 Announce Type: new Abstract: Native decoders limit how pretrained models combine local predictions under new structural constraints. We introduce Structured Re-Decoding (SRD), a training-free framework that constructs local candidates from model scores, sample…
arXiv:2611.14835v1 Announce Type: new Abstract: RF fingerprinting benchmarks report how well a classifier separates transmitters, not whether that separability reflects the individual unit or its hardware family. We compare a benchmark's real hardware grouping with size-matched …
arXiv:2611.15958v1 Announce Type: new Abstract: Static Random Access Memory (SRAM) Physical Unclonable Functions (PUFs) are a promising technology in the realm of random number generation for key generation, but for PUF-based authentication, they have been sidelined due to their…
System One models promise fast, general-purpose decision-making without lengthy token generation. However, understanding their capability spectrum and decision reliability requires more than aggregate performance on current benchmarks. Existing evaluations often provide limited i…
Multimodal coding agents decouple 4D world construction from visual generation, repurposing video models from world generators toward generative renderers. This division of labor raises a fundamental question: if code builds the world, can video models just render it? A reliable …
We present UniSpark-9B, a unified multimodal model that investigates hybrid attention for visual understanding and generation. Built on a Mixture-of-Transformer-Experts backbone with approximately 9B parameters in each branch, UniSpark combines full attention for explicit token i…
arXiv:2611.12935v1 Announce Type: new Abstract: Topic monitoring is the task of labelling the topic of each token in a model's response during generation. Activation-based monitors that run at generation time have so far been trained to detect harmful content and are limited to …
arXiv:2611.12954v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have enabled weight-space programming (WSP), which directly generates neural network weights without gradient-based optimization. However, extending WSP to physical problems remains c…
arXiv:2611.13030v1 Announce Type: new Abstract: Vision-language-action (VLA) policies have demonstrated strong generalization in robotic manipulation, yet processing dense visual tokens often incurs high inference latency. Visual token pruning offers a practical way to reduce th…
arXiv:2611.13127v1 Announce Type: new Abstract: Retrieval-augmented language model systems generally select context by query-conditioned relevance. We argue that long-lived AI systems require a second operator: activation-conditioned memory availability. We specify an architectu…
arXiv:2611.14254v1 Announce Type: cross Abstract: Text-to-image diffusion models can learn and reproduce an individual's identity from only a few reference photos, creating risks of unauthorized and misleading content generation. Proactive defenses address this risk by adding ad…
arXiv:2611.10049v1 Announce Type: new Abstract: LoRA offers a parameter-efficient adaptation strategy, supporting multi-user workloads via customized adapters on a shared backbone. However, serving concurrent requests with different adapters introduces substantial computation an…
arXiv:2611.10403v1 Announce Type: new Abstract: We present QUASI, a newly conceived class of protocols that enable a group of parties to produce a publicly verifiable attestation about a pre-validated statement. Designed for quorum-based systems, QUASI enables parties to attest …