In real-world clinical practice, medical images face open-world shifts: (i) long-tailed rare diseases, (ii) subtle lesions dominated by normal anatomy, and (iii) hierarchical taxonomies. Yet most open-world paradigms assume flat, balanced label spaces, leaving these biomedical demands unresolved. We introduce Generalized Biomedicine Discovery (GBD) and a unified benchmark spanning long-tail, anomaly, and taxonomy-aware discovery. Our key insight is that dominant known patterns form a visual manifold that masks subtle novelty. Inspired by expert diagnosis, we propose SCAN (Surprise-evoked Complementary AccommodatioN), which follows a cognition-inspired perceptual progression: it applies predictive suppression to filter expected norms, triggers surprise-evoked salience to highlight unexpected deviations, and performs complementary accommodation to integrate these shifts into global representations. Extensive experiments show that SCAN improves novel concept discovery while generally preserving established clinical knowledge, and it plugs into existing architectures to better navigate the known-unknown trade-off in medical imaging. Code is available at https://github.com/lytang63/generalized-biomedicine-discovery.
Improving joint audio-visual reasoning in Omni Large Language Models typically incurs substantial data construction and training costs. Our diagnostics reveal multi-hop reasoning difficulties despite correct answers to all corresponding single-hop questions and suggest partial decoupling in the local optimization of perception and reasoning objectives. This motivates post-training with different emphases on these capabilities. Text-only reasoning training yields gains across data sources, model scales, and families. With the best-performing text-only configuration, supervised fine-tuning followed by reinforcement learning (RL) raises Qwen2.5-Omni-7B's geometric mean of nine reasoning scores by 25.83% over the base model, outperforming the complete native audio-visual route with 56.6% fewer GPU-hours. Training on data synthesized entirely by a text-only LLM raises this geometric mean by 21.01% without audio-visual data in construction or training. However, text-only training degrades perception. We therefore propose a text-centric post-training paradigm: text-only training provides the main reasoning optimization, and reduced-data native audio-visual RL then refines perception. Refinement uses about 90% fewer input tokens than full-data audio-visual RL, restores perception above the base level, and retains 93.5% of the best-performing text-only pipeline's reasoning gain.
Each run of an AI-driven research system (ADRS) is an expensive search over a vast solution space, and dependable evaluation requires many runs, making run data both costly to produce and valuable to retain for large-scale analysis. Yet this data remains fragmented: teams operate in isolation, ADRS frameworks emit results in different formats, and no shared infrastructure exists to aggregate or compare runs across problems and systems. We present ROAR, a solution for systematically unifying and analyzing heterogeneous ADRS outputs. ROAR addresses two challenges: reconciling heterogeneous ADRS outputs and enabling analytics across runs with different objectives and scoring functions. We achieve this through a relational schema and parsing layer that normalize heterogeneous ADRS outputs while preserving data lineage and temporal structure, and accommodating new systems without requiring schema modifications. From building a corpus of more than 900 runs from multiple ADRS, we show how pooled data can reveal properties of problem landscapes that are difficult to observe. Consistent with prior work, runs with identical configurations may converge to different scores. We find that many runs realize most gains early, and that the effectiveness of different strategies for incorporating prior solutions into the search process varies across problems. We further show that the pooled corpus is actionable and not merely analytical by using ROAR to configure ADRS runs. Together, these results illustrate how pooled ADRS data can expose problem-dependent structure in search behavior that is difficult to detect from any single system, team, or benchmark. Such cross-cutting insights are difficult to obtain while runs remain siloed; ROAR is the first infrastructure designed to unify them.
For decades, artificial neural networks have operated under the assumption that durable, learned capability resides exclusively in adaptive synaptic parameters, primarily due to the established neurobiology of synaptic connectivity. This design forces models to remain stateless during deployment, incurring well-known limitations such as catastrophic forgetting and expensive retraining. However, recent neurobiological research by Glanzman and colleagues, and others, shows that memories can be transferred between individual organisms in a synaptically independent manner. Inspired by this research, we sought to demonstrate memory transfer of persistent memory between AI model instances, leveraging a neurocentric version of memory. In this paper, we propose NURESA (Neural Unit with Retentive Self-Adaptive Architecture), a novel neural layer that eschews sole reliance on synaptic weight updating by introducing persistent intra-unit memory as a first-class, computational primitive. By structurally separating computation from persistent memory, NURESA enables autonomous memory accumulation and consolidation into transferable stores of memory registers. Experiments across MLP, GPT-2, and modern frontier models like Qwen2.5 demonstrate qualitatively new capability: zero-shot transfer of learned capability into a naive model instance without retraining or access to the original training data; this transfer is enabled by a sparse set of parameters in NURESA's memory register that the model selects on its own based on which neurons were most active. The memory transfer capability of NURESA also protects against domain loss when transformer models undergo learning via fine-tuning. Finally, the memory transfer process completes in approximately one minute even for transformer models with millions to billions of parameters, producing a transfer file orders of magnitude smaller than the original model.
为什么吵架呢? https://theevreport.com/nhtsa-closes-tesla-model-y-steering-wheel-detachment-probe 为车辆在行驶过程中方向盘与转向柱脱落 https://www.tesla.com/support/recall-cybertruck-accelerator-pedal-pad 为加速踏板饰板脱落并可能卡住 The Verge – 8 May 26 Tesla is recalling its cheaper Cybertruck because the wheels might fall off All 173 of the RWD Cybertrucks sold by Tesla are being recalled. 为轮毂连接件存在断裂风险 Business Day ANALYSIS : Tesla blamed drivers for failures of parts it knew were defective Tens of thousands of Tesla owners have experienced premature failures of suspension or steering parts, according to a Reuters review 为控制臂和驱动半轴反复损坏 …… 捷途纵横G700、吉利银河战舰700已经把水下推进器装车并量产发布了,小鹏的飞行器也在试验,但在部分人的口中,它们一文不值……
Deep Reinforcement Learning (DRL) offers learned job selection for High-Performance Computing (HPC), but performance against heuristics alone does not establish value beyond action masking. Six DRL treatments are compared: Proximal Policy Optimization (PPO), Advantage Actor-Critic (A2C), and Deep Q-Network (DQN), each with and without masking. Three heuristics and a seed-paired masked uniform random control provide baselines across ten seeds on two real Slurm (Simple Linux Utility for Resource Management) workload traces, one homogeneous and one heterogeneous, under a common non-parametric framework. All masked treatments complete evaluation, whereas unmasked treatments are truncated. On the homogeneous trace, no masked DRL treatment significantly improves average waiting time or average and maximum bounded slowdown over the control. On the heterogeneous trace, MaskablePPO improves all three metrics relative to the control. Its average waiting time is equivalent to that of the three heuristics within a 10% margin, and its maximum bounded slowdown is 22% lower than that of Last-Come, First-Served (LCFS). MaskablePPO has the leading average waiting-time rank among complete treatments on both traces, but Nemenyi comparisons detect no significant difference from MaskableA2C. Among masked variants, MaskablePPO has the lowest recorded mean training time, while MaskableDQN has the lowest mean decision latency. These findings distinguish completion from baseline-specific scheduling gains and support including a masked random control when assessing the value of learned selection.
之前在各大社区发了下自己被裁员的经历,我就想喷下这些人 很明显是一个公司要求这个岗位的人做不匹配该薪水的事情,被我礼貌的拒绝后,我依然是正常完成工作事务,拿多少钱干多少活,再一边搞自己的副业(因为公司明显就是画饼),然后领礼包,竟然有一堆人共情公司?? 有人带头在维护打工人的权益,竟然还有人在这里拖后腿的?环境就是被你们这群人搞臭的,喜欢舔 boss 是吧
IT之家 11 月 3 日消息,Steam 平台现已公布了最新一周游戏销量排行榜(2026 年 10 月 27 日 - 2026 年 11 月 3 日,无免费游戏),IT之家注意到,《影之刃零》反超此前连冠的《Call of Duty®: Modern Warfare® 4》,同时登顶全球区与国区区榜首,新游《深空当铺:可能是偷的》首次上榜即冲入全球前 5,《足球经理 27》预购版也携 -10% 折扣进入全球榜单。 全球榜单: 影之刃零 Call of Duty®: Modern Warfare® 4 AION 2 深空当铺:可能是偷的 Moon Sweepers EA SPORTS FC™ 27 红色沙漠:增强版 黎明杀机 红色沙漠:增强版 - 未知征途 FINAL FANTASY RESONANCE 国区榜单: 影之刃零 深空当铺:可能是偷的 Call of Duty®: Modern Warfare® 4 《NBA 2K27》 Sons Of The Forest 黎明杀机 Age of Empires IV: Anniversary Edition Moon Sweepers Grand Theft Auto V 增强版 红色沙漠:增强版
Language-guided panoramic video generation benefits various downstream applications, such as interactive 3D scene exploration, virtual reality experiences, and embodied agent training. Existing panoramic generators follow predefined trajectories, and interactive world models act through low-level actions in perspective views. We propose SPW-Nav, a streaming panoramic world model that understands movement instructions and streams one minute of 2K 360-degree video in real time from a single panorama. SPW-Nav interprets each instruction in the previously generated panorama as camera motion. Spherical rotation decoupling applies rotation exactly on the sphere, pose-aligned conditioning keeps translation inputs bounded over long streams, and a multi-term memory with a few-step generator continues the scene as instructions change. We also build SPW-NavSet, panoramic videos with camera trajectories and verified instructions. Driven by language, SPW-Nav outperforms prior panoramic generators in camera-following accuracy and video quality, and supports on-the-fly instruction switching.
The recent emergence of Time Series Foundation Models (TSFMs) has significantly advanced multi-step forecasting performance, enabling accurate predictions over extended future horizons. However, existing TSFMs often suffer from significantly inherent uncertainty, which typically manifests as derived forecast branches emerging at each time step and spreading to subsequent steps; different forecast branches often exhibit varying forecasting performance, thereby undermining the credibility of TSFM forecasts. In this paper, we propose the Slicing-Graphing-Alignment (SGA) method to quantify the uncertainty of multi-step TSFM forecasts. The proposed SGA first characterizes the topology of all potential forecast branches using a directed acyclic graph, such that the graph complexity bounds the uncertainty of multi-step forecasts, and then precisely measures the graph complexity by integrating both topological information and TSFM-inherent stochasticity. Experimental results conducted on 11 TSFMs and 27 datasets demonstrate that (i) SGA achieves the best performance when ranking predictive errors with uncertainty estimates; (ii) SGA works with a more extensive and more precise sampling coverage than those of existing UQ methods, deriving a quantification mechanism fundamentally different from those of established ones; and (iii) larger model scales of TSFMs correlate with lower uncertainty estimates of multi-step forecasts, suggesting another empirical scaling law for uncertainty quantification of multi-step TSFM forecasts.
Survival analysis estimates time-to-event outcomes from patient covariates and is widely used for medical risk assessment. Patients seeking prognostic information after a diagnosis may turn to large language models (LLMs), now readily accessible through consumer applications. However, whether LLMs can provide accurate survival predictions has not been rigorously evaluated. We introduce Survprompt, a framework that converts structured patient covariates into free-text clinical vignettes and prompts pre-trained LLMs to predict survival zero-shot. We benchmark Survprompt against conventional survival models, including random survival forests (RSF), across two multi-institutional pan-cancer cohorts: the publicly available MSK-CHORD cohort and a newly curated cohort from the Providence St. Joseph Health Network constructed using an LLM-based medical abstraction framework. We report censored mean absolute error (cMAE) and concordance index (c-index) and conduct feature ablations to identify variables influencing LLM predictions. Frontier LLMs achieved surprisingly competitive cMAE for individual survival times. For example, GPT-5.6-Sol achieved cMAE within 10% of state-of-the-art RSF models specifically trained for survival prediction for several cancer types and lower cMAE than RSF for prostate cancer in MSK-CHORD. Feature ablations revealed that LLMs prioritized clinical variables similarly to specialized survival models. However, LLMs showed inconsistent accuracy across cancer types and institutions and poorly discriminated between high- and low-risk patients (lower c-index). Zero-shot LLMs can generate surprisingly accurate prognostic estimates without specialized training, but their variable performance across cancer types and institutions remains an important limitation for clinical use.
Multimodal large language models (MLLMs) increasingly serve as judges in training and evaluation pipelines, often assessing answers together with explanations. Although AI judges are sensitive to textual factors, it remains unclear whether ordinary plausible explanations can sway judgments requiring visual verification. We introduce JUPE, a visual-question-answering (VQA)-style benchmark that fixes answers while varying explanations. Across 14 MLLM judges, ordinary explanations that sound plausible mislead judges, with effects comparable on average to deliberately persuasive arguments. Plain justifications and chain-of-thought rationales reduce rejection of incorrect answers by 12.7 and 13.8 percentage points, respectively. We call this failure plausibility capture. Using signal detection theory, we find a significant mean shift in decision criterion toward acceptance, without a clear change in mean discriminability. Explanations sway judgments across domains, explanation generators, and judging protocols, while tested mitigations offer limited, model-dependent protection. Such shifts can inflate performance estimates when judges evaluate answers with explanations.
Video Large Language Models(VLMs)在视频理解与推理方面展现出强大的能力,但处理长视觉序列会带来显著的计算、时延和内存开销。本综述考察免训练推理加速,重点是在降低推理成本的同时保留与任务相关的时空证据。我们按照在推理流水线中的干预阶段来组织现有方法,涵盖输入、视觉编码、projector、prefill 和 decoding。Post-training quantization(PTQ)作为跨阶段扩展单独讨论,其校准需求各不相同。我们分析干预位置如何影响证据保留与计算节省,以及为何局部效率提升未必能转化为端到端加速。我们结合已有研究的定量证据以及我们在统一评估设置下开展的自身实验来补充该分析,以评估准确率-时延权衡。
Topology reasoning jointly detects 3D lanes and traffic elements from multi-view images and infers their structural connectivity. Current methods model lanes as discrete polylines, lacking smoothness, analytical tangent directions, and global spatial support for attention, while providing sparse topology supervision. We propose TopoCurve, a geometry-driven architecture for 3D topology reasoning grounded in a structured parametric lane representation. Lanes are modeled as endpoint-fixed cubic B\'ezier curves, enabling continuous geometry with exact endpoints and analytically defined directionality. We exploit this shared curve geometry across the entire pipeline. Endpoint distance and tangent alignment are encoded with multi-scale Fourier features and injected into the topology head. Sampled curve points serve as geometry-aligned references for deformable cross-attention spanning the full lane. Parallel curve-anchored attention branches provide diverse predictions for one-to-many topology supervision. These components form a tightly coupled cascade where representation enables geometric reasoning, guides feature aggregation, and supports denser supervision. TopoCurve achieves 50.6 OLS on the OpenLane-V2 benchmark without any post-processing, establishing a new state-of-the-art among end-to-end camera-only methods, and outperforms all existing approaches on endpoint detection (56.8 vs. 52.6 on DET_p).
Put Yourself in the Viral Angry Dance — From One Photo Angry Dance Filter AI turns a single photo into the TikTok-famous angry dance clip. Same attitude. Same moves. No dancing. No editing. No prompts. Why it hits 1 photo in → vertical AI dance video out Shot-for-shot from the viral Angry Dance Filter routine Ready for TikTok, Reels & Shorts Failed renders refunded · credits never expire · no subscription How it works Upload one clear photo (or scan a QR and send it from your phone) Tap generate Download your clip in a few minutes and post it Best with one person, face visible, waist-up or full-body. Try it 👉 Angry Dance Filter AI One photo. A few minutes. One very loud group-chat reaction.
iPhone 18 Pro 屏下 Face ID 识别率感觉有所下降,不像自媒体说的解锁率一致。 人脸重录过 系统升级过 大角度转头重录过 眼镜佩戴录入过。 没贴防窥膜,就普通钢化膜。 Apple Watch S12 联动解锁的开关也开了,但是这功能仅限面部遮挡情况下。 最后解锁率还是相较以前的手机低。 经常开屏就是密码,感觉小白鼠感有点拉满。
Startups are naturally good at this; it is hard to keep a bigger company good at this and i think an underexplored space. pranav@prd_008 OpenAI's superpower is the ability to swiftly assemble an empowered group of highly capable people to work on the most important and urgent thing at any point of time. No one really cares for org lines. It's how we stay nimble, seize opportunities, and recover from mistakes. 🔗 View Quoted Tweet
地址: https://remox.ai/ 我所在的公司开发商业 App 。这是我作为 OPC 独立完成的第一个项目。 remove.bg 的 API 将于 12 月停止服务,因此我想做一个替代方案。我把公司内部的 API 封装后对外提供服务。借助商业 App 共享的机器池资源,可以分摊成本,在保证 AI 能力的同时提供较好的性价比和稳定性。 项目初期会赠送大量积分。评论区留言“mark”,即可申请 500 次 API 图片去背景额度,有效期一年。 如果你有这方面的 API 需求,欢迎试用。后续我还会陆续封装更多 AI 服务