AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.16058v1 Announce Type: new Abstract: Red-light violations and harsh braking at signalized intersections are major contributors to traffic accidents. This paper analyzes and predicts human driver decision-making and longitudinal trajectory behavior during traffic light signal transitions. We collected a diverse real-world dataset comprising 449 approach runs under varying speed and distance conditions. Vehicle motion was recorded using RTK-corrected GNSS with centimeter-level accuracy, and driver heart rate and multi-level comfort ratings were monitored. Spatial and temporal calibration ensured precise alignment between vehicle state and signal timing. Statistical analysis identifies required deceleration as the dominant single predictor of the stop-g…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.16057v1 Announce Type: new Abstract: Unified multimodal large language models (MLLMs) and multi-agent systems have advanced visual generation. However, three limitations remain. (1) Existing methods often distill task-specific experience with limited generalizability. (2) Reflection is often deferred until task completion. (3) Knowledge is often acquired only in response to downstream task demands. To address these limitations, we introduce OmniHarness, a framework for generalizable visual generation via symbolic policy learning. OmniHarness abstracts verified executions into symbolic policies for visual generation task families, capturing shared procedures and applicability conditions while removing instance-specific inputs. The harness instantiates…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.16056v1 Announce Type: new Abstract: Humans carry behaviour knowledge of how to act in familiar situations into every new task rather than relearning it from scratch. There is no reason a Reinforcement Learning (RL) agent shouldn't do the same: known behaviour patterns need not be learned, only applied. Neuro-symbolic RL bridges prior knowledge and RL by injecting symbolic knowledge alongside a learned policy. The point at which this knowledge is integrated is critical: a poor choice can produce, for instance, hallucinated preconditions, which surface as safety and reliability problems in agents acting in changing environments. We formalise this behavioural knowledge as a precondition Bayesian network (BN) over the agent's \emph{structural actions} -…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.16054v1 Announce Type: new Abstract: Transformer-based multi-target tracking (MTT) jointly learns data association and state estimation, but MT3/Track-MT3-style trackers repeatedly re-encode measurement windows, incurring redundant computation. We propose Causal Neural Set Filtering (CNSF)\footnote{\href{https://github.com/daihuangyu/CNSF}{Code: https://github.com/daihuangyu/CNSF}}, a neural set filter that encodes only current measurements while carrying past evidence in a structured recursive track state. CNSF combines exclusive Sinkhorn association, association-conditioned Kalman-shaped updates with moment matching, and recurrent Bernoulli lifecycle modeling with measurement-driven birth. These mechanisms impose soft one-to-one constraints, propag…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.16247v1 Announce Type: new Abstract: Large language models sometimes behave in ways resembling human emotional responses, and recent work has identified internal representations that may explain this. We ask whether LLMs represent pain distinctly from fear, sadness, and generic negative valence, and whether this representation functions as pain would be expected to. We build a dataset describing painful situations across five categories: physical, psychological, social, moral, and cognitive. These are paired with controls for fear, negative emotion, negative world states, sadness, non-painful bodily sensation, arousal, numbness, and neutral content. Using denoised difference-in-means, we extract a linear pain direction from 25 open-weight models acro…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.16245v1 Announce Type: new Abstract: Long-horizon scientific discovery requires agents to alternate between exploration, disciplined execution, and critical reassessment as evidence changes. Current language models are trained primarily on the products of science and optimized using outcome-level signals, providing limited supervision for these process-level shifts in scientific judgment. We investigate whether such judgment can be recovered from scientist interaction traces and used to control the internal computation of a frozen frontier model. Using contrastive interventions collected during real scientific research, we identify a coordinated, low-dimensional control structure within Kimi 2.6, a trillion-parameter mixture-of-experts model. Residua…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.16232v1 Announce Type: new Abstract: Geospatial artificial intelligence (GeoAI) powered by large language models (LLMs) is expanding the capacity to query, generate, and interpret spatial information through natural-language interfaces and agentic autonomous GIS workflows. This capability creates governance challenges that general AI ethics discussions do not fully capture, including passive location inference from mobility traces, spatially structured bias amplification driven by spatial autocorrelation and scale effects, hallucinated spatial facts, and uncertainty compounding across multimodal geospatial inputs. This narrative review identifies eight recurring issues in LLM-enabled GeoAI: data provenance and consent, spatial privacy and inference r…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.16215v1 Announce Type: new Abstract: GPU high bandwidth memory is scarce and expensive, and KV caches consume much of it as chats, agent loops, and document question answering accumulate state. Systems such as Mooncake, LMCache, FlexGen, InfiniGen, and AttentionStore extend GPU memory with CPU DRAM and SSD. The harder question is which blocks belong in each tier, when to move or evict them, and whether prefetching helps. We study these choices in a discrete event simulator spanning GPU HBM, CPU DRAM, and SSD, calibrated against a random forest execution time predictor. We compare recency, reuse frequency, predicted reuse, and an EWMA predictor with prefetch lookahead across chat, agent, and document question answering workloads. Tiering supports 73.0…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.16213v1 Announce Type: new Abstract: Artificial intelligence is reshaping biological research across an increasingly connected digital-to-physical workflow. General-purpose large language models can retrieve and integrate scientific information, support experimental planning, and computational analysis; biological foundation models can predict, optimize, and generate proteins, genes, and genome-scale sequences; agentic systems can coordinate multistep research tasks; automated laboratories can partially close the design-build-test-learn cycle. These technologies could greatly benefit medicine, public health, and biotechnology. However, their biosecurity risk depends not only on what the AI can do, but also on who uses it, their expertise and intent,…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.16206v1 Announce Type: new Abstract: Disaggregated LLM serving places compute heavy prefill and memory heavy decode on separate GPU pools. Systems such as DistServe, Splitwise, and Mooncake make this separation fast, but routing still determines which instances handle each request. We study a router that estimates the additional completion time on each instance using exact prompt length, predicted output length, post admission KV cache pressure, and SLO class. We develop the policy in a discrete event simulator and validate it on eight NVIDIA A40 GPUs, each running a vLLM engine, with NIXL transferring KV caches between pools. All workloads run at measured saturation. Across three mixed, bursty arrival traces, the calibrated router achieves the highe…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.16189v1 Announce Type: new Abstract: Open-ended strategic wargames are high-stakes LM-based social simulations: they model adversaries, institutions, escalation, plan brittleness, doctrine, and crisis response. Language models (LMs) are attractive because they can play agents, generate scenario branches, adjudicate ambiguous actions, and summarize lessons, but the same affordances make open-ended roles dangerous: model language determines both what an actor attempts and what becomes simulated reality. This position paper argues that no LM-enabled wargame should inform planning, doctrine, policy, or crisis response without an auditable safety case, and that the proper use of open-ended wargames today is to stress-test decision-influencing LM agents. W…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.16163v1 Announce Type: new Abstract: The sharp increase in mass shootings underscores an urgent need for systems that guide victims to safety in real time. An effective evacuation system must minimize threat exposure while also accounting for adversarial uncertainty and crowding dynamics. Current methods in the literature are rigidly constrained to layout-specific policies and computationally intractable in large-scale layouts, while practical guidelines simply advise victims to "run", "hide", or "fight". We propose GPEvac: a GNN-based PPO framework that computes adaptive evacuation routes during shooting events. To capture both local and long-distance dependencies, we introduce an edge-first sequential message-passing scheme with a learnable virtual…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.16145v1 Announce Type: new Abstract: We study a practical question: can a small correction module fix errors in a frozen language model's outputs without degrading its base capabilities? We propose CRN v2, a lightweight logit-level correction module (~34M trainable parameters, 0.73% of the 4.65B text module) that sits atop a fully frozen Gemma 4 E2B model. The base model is never updated; only the correction module learns, via supervised fine-tuning followed by reference-free DPO on 83,400 error-correction pairs. On a 60-question domain exam (CEHRI: Certified Human-Robot Intelligence, covering facts, arithmetic, and implicit-goal reasoning), CRN v2 corrects 53.3% of base-model errors (reworded variant: 43.3%) while showing no degradation on tested ca…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.16129v1 Announce Type: new Abstract: A new scheme for parameter pruning is introduced, derived from the differential-geometric distance in model space. Pruning a parameter sets its value to zero, representing a displacement of the model to the hypersurface on which that parameter vanishes. The minimal distance from the unpruned model to this hypersurface is naturally computed via the geodesic distance in the model space as determined by the Fisher information metric. This distance determines the true change in the model, and its performance, under pruning. By analysing progressively more faithful approximations of this geodesic distance a natural hierarchy of optimality for pruning methods is determined. This starts with the traditional magnitude pru…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Naoki Egami has become a standout in political methodology, helping refine tools that give scholars durable results.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Discussion | Link

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Every family photo you ever posted would be fair game for AI companies unless you choose to opt out Leaked documents from a government proposal show that the Albanese government is considering reversing the fundamental rights of Australians under copyright law. The proposal refers to an “opt-out model”. This would give AI companies permission to train on the open internet here in Australia. Every family photo you ever posted, every small business website, every website would be fair game for AI companies unless you choose to opt out. Continue reading...

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Discussion | Link

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Discussion | Link

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Conversational Large Language Models are post-trained on language that expresses specific behavioural traits, such as curiosity, open-mindedness, and empathy, and values, such as helpfulness, harmlessness, and honesty. This is done to increase utility, ensure safety, and improve the experience of the people interacting with the model. However, values are complex and inter-related – inducing one could modify behaviour on another. Further, inducing certain values can make models more addictive or sycophantic through language used in the generations, with a potential detrimental effect on the…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Diffusion large language models are a compelling alternative to autoregressive models, yet existing RL methods for diffusion treat all denoising steps as equally important and rely on biased, high-variance likelihood estimates. We identify two fundamental weaknesses: the absence of temporal credit assignment across the denoising trajectory, and the systematic bias of mean-field likelihood estimates used for policy optimization. To address these, we propose Denoising-Aware Credit Assignment for GRPO (DACA-GRPO), a lightweight, plug-and-play enhancement for any GRPO-style trainer. DACA-GRPO…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Enterprise data lakes accumulate tables faster than human stewards can document or classify them, leaving columns with missing descriptions and unassigned governance labels. This documentation debt undermines data discovery, access control, and regulatory compliance. We present Glyph, a production system that frames two coupled problems, column description generation and column type annotation for data classification, as cooperating LLM agents orchestrated as stateful graphs. The Descriptor grounds generation in the pipeline source code that produces each column, retrieved on demand from an…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Moving from closed to open source models can take weeks, not years. A five-stage playbook: discover, evaluate, adapt, decide, and production.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive. Naively persisting entire conversation histories is both token-inefficient and counterproductive—irrelevant context degrades generation quality. We introduce shared selective persistent memory, a memory architecture for agentic systems that identifies and retains four categories of reusable context—task specifications, data…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：This week on the a16z show, Greg Brockman, president and co-founder of OpenAI, made the point that developers have been The post OpenAI president: “The computer should be there to empower you.” So stop retooling software for AI agents appeared first on The New Stack.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Poll data released Tuesday by the New York Times and Siena University confirms what we've already been seeing, and what politicians are responding to - AI and data centers are incredibly unpopular. Asked if they support or oppose the construction of data centers to power AI tech, 61 percent of the 1,503 likely voters surveyed in early September (ahead of the recent AI safety slowdown discussion) said they were opposed, with only 14 percent saying they strongly support. The split was about even among 2024 Donald Trump voters, at 49 percent support to 45 percent oppose, while people who had voted for Kamala Harris or who didn't vote leaned opp … Read the full story at The Verge.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Discussion | Link

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯： Tool: Gemini Live audio Google released Gemini 3.8 Live and 3.8 Live Extended Thinking today - two new speech-to-speech models that are a similar shape to OpenAI's GPT-Live family. I pointed GPT-6 Astra Extra High at the documentation and had it build me this web UI for trying out the new models. You can select a model and voice preset, enter an optional system prompt and then start a voice conversation through your browser, including the ability to interrupt the model while it is talking. The implementation uses no libraries. It connects to the wss://generativelanguage.googleapis.com/ws/google.ai.generativelanguage.v1alpha.GenerativeService.BidiGenerateContent?key=... WebSocket endpoint and uses a Web Audio API AudioContext for both capture and playback. Here…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：A former Anthropic researcher’s apocalyptic declaration about artificial intelligence has led to a global panic that the technology might be the end of us all. At an event in Washington today to warn about the dangers of AI, US senator Bernie Sanders said that Congress has been ‘asleep at the wheel'. Oddly, Steve Bannon appeared at the same event. But is this response a distraction from the more immediate problems AI is already causing? Kai Wright and Carter Sherman are joined by Guardian tech reporter Johana Bhuyian to put this moment in context, and she explains why we should be cynical about industry calls for regulation Continue reading...

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Know everything. Do anything. That was the message NVIDIA founder and CEO Jensen Huang brought to Salesforce Dreamforce Tuesday, joining CEO Marc Benioff onstage in an appearance that coincided with the announcement of Koa — Salesforce’s first CRM reasoning model, built on NVIDIA Nemotron 3 Super. Huang didn’t just take the stage. He walked into […]