DPS (Dual-Mode Precision LLM Serving) is a system that treats model‑weight memory as elastic by using a multi‑precision representation. Under normal load it serves the full‑accuracy model, but when KV‑cache pressure spikes it switches to a lower‑precision variant and reallocates unused weight memory for KV cache blocks. Built on Semi‑Unified Memory and implemented on top of vLLM, DPS boosts sustained throughput by 2.1–3.3× and effective pass@1 by up to +41 pp over static FP16 while maintaining FP16‑class accuracy.
SkillPE is a prompt‑engineering framework that evolves reusable cinematic skills from expert‑authored seeds to improve text‑to‑video generation for non‑experts. It encodes shot logic, composition, lighting, sound design, and other filmmaking cues in a fine‑grained format, and uses movie references classified as resonators, dissonants, and divergents to refine skill application and inspire creative alternatives. Experiments on StoryEval and VBench demonstrate up to 1.40‑point gains over the strongest baseline and 0.51 points over seed skills on a 7‑point four‑dimensional evaluation, while remaining competitive on benchmark‑native metrics.
The projection of queries and keys are central to the attention mechanism in Transformer architectures. While they are mathematically symmetric, they play different roles in attention mechanisms.
The article reports a failed MX Keys Mini pickup where a customer, Usman, arrived at the building at 9:15 but was not met, leading to a negative rating. The author acknowledges that an auto‑reply incorrectly confirmed the author's presence at 9:27, worsening the situation, and has apologized on behalf of the account. They are considering disabling auto‑replies that promise the author is home when they cannot confirm it.
The study investigates how prompt template choices during Knowledge Distillation (KD) affect safety alignment in language models. It finds that using chat templates during KD degrades safety alignment, making models more compliant with harmful queries, while non-chat templates better preserve the base model’s internal representations. These effects are observed across LLaMA, Gemma, and Qwen families on multiple safety benchmarks.
By Anjila Budathoki, Manish Dhakal, Benjamin M. Ampel, Yi Ding
CCRV-Bench is a constraint‑driven benchmark designed to evaluate visual causal reasoning in vision‑language models on single‑image physical scenarios. It assesses four causal task dimensions—causal relation discovery, state prediction, causal diagnosis, and intervention—while applying constraints such as entity symbolization, spatial grounding, factual adversarial constraints, and minimalist output constraints to reduce shortcut learning. Experiments on 15 multimodal models reveal that constraint sensitivity varies by task and model, with intervention and spatial grounding having the largest impact and factual adversarial constraints improving causal diagnosis across models.
By Linyuan Gao, Yuan Wu, Yi Chang
Auteur is a language‑driven method that generates human‑centric camera framing for generative video models. It treats shots as framings relative to an actor, encoding shot size, angle, and composition as functions of human pose and motion, and uses a domain‑specific language that converts to standard 6‑DoF camera parameters. A fine‑tuned multimodal large language model acts as a virtual director, mapping natural language descriptions and coarse human motion to sparse DSL keyframes that are interpolated into continuous camera trajectories for video generation.
By Muhammed Burak Kizil, Enes Sanli, Niloy J. Mitra, Xuelin Chen, Erkut Erdem, Aykut Erdem, Duygu Ceylan
PhysElite is a new bilingual multimodal benchmark designed to evaluate large language models on Olympiad-level physics problems. It contains 11,586 problems, each paired with visual diagrams, step-by-step bilingual Chinese‑English solution derivations, and the final answer. Benchmarking 18 models revealed that even the best reaches only 33.7% accuracy, and a step‑level analysis highlights where models falter in reasoning.
By Ruoran Xu, Wending Gao, Liyunfeng Chen, Aixin Shi, Haoyu Cheng, Zixiang Fang, Yiqiang Zou, Qiufeng Wang
SatNav is a new, scalable benchmark for long‑horizon vision‑language navigation (VLN) with unmanned aerial vehicles (UAVs), built from high‑resolution satellite imagery. It generates 118,000 navigation episodes across 59 scenes in 18 cities, using satellite crops to approximate UAV nadir views and featuring three task families—Boundary, Landmark, and Route—to test long‑term memory and geospatial reasoning. The benchmark also introduces SwiftVLN, a modular framework for memory component experimentation, and demonstrates that models trained on satellite data can transfer to real‑flight UAV observations.
By Jiajun Jiang, Chunliang Hua, Zichun Chen, Yanxing Wu, Zeyuan Yang, Jie Song, Xiao Hu
The paper investigates when a language‑model judge can truly ground its verdicts in code correctness. It shows that current multi‑agent verification methods rely on evidence that is both independent of the answer and distinct between candidates—conditions that fail in code judging. By analyzing two label‑free measurements from the judge’s logs, the authors demonstrate that gating on one measurement allows the system to decline uncertain comparisons, improving accuracy from 20.7% to 36.9% while still answering half of all cases.
By Salma Roshdy Aly, Hussein Assaf, Ziad Kobti
The paper introduces CamVLM, a framework that equips large vision‑language models with the ability to actively control camera viewpoints for improved surveillance video understanding. It presents two new datasets: CCTV‑Anomaly, a large‑scale surveillance video collection with detailed captions and event annotations, and CamTrack‑53K, an object‑centric viewpoint trajectory dataset for learning camera actions. Using reinforcement learning, CamVLM learns long‑horizon observation strategies, achieving state‑of‑the‑art performance in both passive and dynamic viewpoint settings.
By Xiao Zhang, Wang Zeng, Sheng Jin, Wentao Liu, Chen Qian, Shichao Kan
The paper introduces SGMA, a structure‑guided masked autoencoding framework designed for ultra‑high‑resolution scientific images. SGMA combines a content‑adaptive quadtree tokenizer that reduces gigapixel images to a fixed‑length sequence with a structure‑conditioned masking process that focuses reconstruction on spatially informative regions. The method, enhanced by Damped Accumulation to stabilize multi‑scale signals, achieves superior performance over standard MAE baselines on electron microscopy, whole‑slide optical microscopy, and X‑ray CT datasets, delivering significant accuracy gains and up to a 24.8× inference speedup.
By Enzhi Zhang, Du Wu, Rui Zhong, Cong Ma, Isaac Lyngaas, Amir Koushyar Ziabari, Xiao Wang, Peng Chen, Tao Luo, Toshio Endo, Fumiyoshi Shoji, Kento Sato, Kentaro Uesugi, Takayuki Nonoyama, Ryuji Kiyama, Masahiro Yoshida, Masaru Tezuka, Tetsuya Ishikawa, Satoshi Matsuoka, Masaharu Munetomo, Mohamed Wahib
The paper introduces Auto-Comp, a fully automated, concept-driven pipeline that generates photorealistic compositional benchmarks for vision‑language models. Auto‑Comp creates paired Minimal and Contextual samples for each concept, enabling isolation of core binding abilities from visio‑linguistic complexity. Evaluations across 25 models reveal consistent failures in attribute and relational binding, with context helping relational tasks but hindering attribute tasks due to visual clutter.
By Cristian Sbrolli, Toshihiko Yamasaki, Matteo Matteucci
Self-Play Search Distillation (SPSD) is a framework that generates superhuman synthetic data by having MuZero-like networks play board games in executable environments. The search records are converted into structured reasoning chains that serve as environment‑grounded supervision for training large language models. When applied to Qwen3‑4B‑Base, SPSD improves performance on six mathematics benchmarks from 24.1 to 36.6 and raises the win rate on unseen games from 15% to 45%.
By Lorenzo Molfetta, Wai-Chung Kwan, Giacomo Frisoni, Luca Ragazzi, Gianluca Moro, Pavlos Vougiouklis, Jeff Z. Pan, Pasquale Minervini
The paper "Financial Fragility in Societies of LLM Agents: Coordination Failures and Stabilizing Mechanisms" investigates how large language model agents can collectively cause financial failures when making individual protective decisions. Using the FRAIL framework, the authors simulate bank runs, debt rollovers, and reward crowdfunding, finding that 77% of bank-run and 83% of debt-rollover episodes fail even without malicious agents. They test three interaction mechanisms—compensated commitments, centralized agreements, and participant-led coalitions—each improving outcomes but none dominating across all scenarios, noting that early broad commitments are key to successful stabilization.
By Zhenhao Fu, Ruipeng Xu, Qibing Ren
The paper introduces mutable transcripts, an interaction paradigm that lets users edit prior turns in a chat, turning the conversation history into an editable state rather than a fixed record. A prototype was built and tested with 17 participants, who preferred mutable transcripts over standard chat for clarity, confidence, and ease of use, and reported less need to restart conversations. Analysis of user study transcripts shows that mutable transcripts can shorten conversations and remove outdated context, suggesting that user-driven revisions improve interaction quality.
By Dan Barry, Andrew Hines
Cartograph is a federated Model Context Protocol (MCP) proxy that reduces AI agent tool discovery from linear catalog traversal to progressive disclosure, exposing only a few proxy tools instead of all definitions. It uses operator-attested capability cards, a three-layer confusable-cluster analysis called Rift, and a two-stage retrieval process to rank servers before tools. In a 22-server, 374-tool deployment, Cartograph achieves higher recall (R@5 = 0.816 vs. 0.592) and drastically fewer tokens (475 vs. 42,450) for discovery exchanges, with minimal latency overhead.
By Justice Owusu Agyemang, Michael Agyare, Kwame Opuni-Boachie Obour Agyekum, Kwame Agyeman-Prempeh Agyekum, Francisca Adoma Acheampong, Jerry John Kponyo
CARGO is a framework for evaluating agentic AI systems in production that addresses the problem of reference-instance divergence (RID), where reference-based judges penalize correct answers that involve different entity identifiers. It treats retrieved references as procedural exemplars, grounds judgments in the live instance’s context, assigns a three-way status to claims, and gates evaluation by retrieval confidence. Using the CARGO-Bench diagnostic suite, CARGO eliminates false penalties and improves discrimination while revealing a limitation in detecting procedural corruptions.
By Mukul Chhabra, Shail Patel, Luigi Medrano
The paper proposes Metric-based Loss Weighting to enhance visual grounding in multimodal machine translation. By increasing loss for tokens that benefit from image context—identified via the Point-wise Cross-mutual Information (PCXMI) metric and its Congruency-based variant—the method improves translation accuracy on the CoMMuTE dataset by over 7 percentage points. Experiments fine-tune three pretrained multimodal LLMs across three language directions, showing superior performance compared to standard fine-tuning while preserving overall translation quality.
By Pawe{\l} M\k{a}ka, Piotr Andruszkiewicz, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis
The paper introduces a blockchain-backed agentic security framework that protects the entire software development lifecycle and the AI components monitoring it. It coordinates specialized security agents—covering source integrity, dependency and SBOM analysis, CI configuration auditing, artifact verification, and runtime policy evaluation—each powered by a large language model that interprets artifacts, reasons over tool outputs, and generates structured security reports. Every agent produces a cryptographically signed attestation recorded on a permissioned blockchain via smart contracts, creating an immutable attestation log, an agent registry, and an enforceable release‑policy module, while communication is secured through a consortium‑operated certificate authority.
By Toqeer Ali Syed, Asadullah Abdullah Khan