Strumień wydarzeń
Wszystko, co pojawiło się w monitorowanych źródłach – od najnowszych.
-
Hunger beats tenure: Advice for junior engineers
115 punktów · 96 komentarzy · autor akavi · felixrieseberg.com
-
Early progress on accelerating drug development with Claude
322 punktów · 336 komentarzy · autor dataking · www.anthropic.com
-
Raspberry Pi Zero 3W and Pi 4 Model A spotted in device trees
215 punktów · 137 komentarzy · autor sthlmb · bret.dk
-
Code-execution flaw in UEFI firmware threatens most servers on planet Earth
303 punktów · 222 komentarze · autor DamnInteresting · arstechnica.com
-
Four Months of Zig
176 punktów · 137 komentarzy · autor ibobev · gracefulliberty.com
-
Tailscale SSH: Investigation and remediation update
378 punktów · 189 komentarzy · autor figmert · tailscale.com
-
Survival LLM: AI assistant and emergency library that runs on your own computer
516 punktów · 194 komentarze · autor Luc · www.brangus.io
-
US President says he will ban the term 'artificial intelligence'
106 punktów · 134 komentarze · autor anigbrowl · thehill.com
-
Magnituda 5,4 — 210 km ENE of Nagqu, China
Głębokość 10 km.
-
Discord will soon let anyone find public server messages through Google
322 punktów · 197 komentarzy · autor DeepLogin · discord.com
-
Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction
[Widzenie komputerowe] Autorzy: Prakhar Kaushik, Soumava Paul, Alan Yuille Novel view synthesis and 3D reconstruction have advanced rapidly with radiance fields and splatting, yet their memory and computational demands limit their use in resource-constrained settings. We introduce Hexels: novel planar hexagonal surface elements with a first-order spatial color field for efficient 3D scene and 2D image representation. Hexels exploit locally planar regions with smoothly varying appearance using fewer, larger primitives. Their hexagonal support provides an area- and boundary-efficient domain, while the local color field captures appearance variation within each primitive. Across 34 scenes, Hexels improve PSNR over memory-matched 2DGS by 4.53-7.38 dB across datasets while requiring lower training VRAM. We further ablate Hexels by showing that per primitive, Hexels outperform 2DGS by upto 4.74 dB while using lower training VRAM and having 2.31 times faster FPS. Eve…
-
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning
[Robotyka] Autorzy: Chaehyun Kim, Chi-Pin Huang, Jisoo Kim i 4 więcej Vision-Language-Action (VLA) models have made substantial progress in robotic manipulation, but their generalization remains constrained by the diversity and coverage of action-labeled robot demonstrations. Human videos provide much broader behavioral and environmental experience, while learning from them faces a fundamental trade-off between scalable data and explicit action grounding. We introduce ThinkWorld, a VLA learning framework that grounds action reasoning in world dynamics and strengthens it through reinforcement learning with world imagination. ThinkWorld represents each action thought as a Chain-of-Dynamics (CoD), a sequence of discrete motion tokens that captures the intermediate dynamics connecting the current world to a future state and serves as a common action representation across embodiments. We first initialize CoD with action-labeled demonstrations, then predict the…
-
An EVM-Cosmos Bridge for Atomic, Semantic-Preserving Transfer of Environmental Tokens
[Inżynieria oprogramowania] Autorzy: Sebastian Pandolfi, Guzmán Llambías, Laura González Transferring semantically typed tokens between heterogeneous blockchains (e.g. EVM and Cosmos ecosystems) raises two problems: semantic mixing, the loss of a token's domainspecific meaning in transit (e.g., CO2 removals issued under different methodologies), and atomicity despite divergent consensus and timing assumptions. We propose a bridge that addresses both. A deterministic indicator identity derived from cryptographic commitments, mirrored in class registries on both chains and checked at mint time, preventing semantic mixing by construction. For atomicity, we extend hash time-locked contracts (HTLCs) from two-party exchange to single-owner transfer with an automatic callback that burns the source escrow after a destination claim, and a protocol-minimum bounty that makes the fallback burn incentive-compatible even against adversarial senders. We machine-check the protocol's invari…
-
Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness
[Uczenie maszynowe] Autorzy: Igor Shilov, Xiaoxue Yang, Alexander Panfilov i 6 więcej We introduce Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small set of learned per-head attention gates. HoS learns how each head should redistribute attention between trusted and untrusted tokens, enabling models to reason over untrusted content without following injected instructions. We evaluate HoS on Llama-3.3-70B-Instruct and GPT-OSS-20B. We compare it against SecAlign++, a state-of-the-art finetuning-based defense, and ASIDE, a defense that, like ours, builds instruction-data separation into the model architecture. We show that HoS offers greater robustness to adaptive attacks, better performance on standard utility benchmarks, and matches top performance on standard agentic prompt injection benchmarks. More specifically, the black-box RL-Hammer attack reaches 97% ASR against GPT-OSS-20B and 85% against SecAlign, but only 10%…
-
Attention as Lattice Gauge Theory: Relations Interact Only Through Wilson Loops
[Uczenie maszynowe] Autorzy: Aakash Sarkar, Ananya Mukherjee, Motoshige Sato Relations compose through the entity they share - Alice is Bob's mother and Bob is Carol's father, so Alice is Carol's grandmother - and the order matters, since a father's mother is not a mother's father; verifying a composed relation means closing the loop. We show that if each entity's coordinate frame may be rotated independently (per-entity frame freedom), three things follow. In the pure-gauge sector, relations that share no cycle cannot interact at all. The only gauge-invariant score of a triangle is a class function of its holonomy $H = T_{ij} T_{jk} T_{ki}$ - a Wilson loop. And the only equivariant update of an edge is $U = Ψ(H)\, T_{ij}$ with $Ψ$ conjugation-equivariant. Edge attention by Wilson loops is therefore not one design among many but the unique form the symmetry permits. Three communities hold pieces of this form: the commuting-operator embeddings of knowledge graphs…
-
KPPax: preprocess differentiable kinetic ODE for machine learning in atmospheric chemistry
[Sztuczna inteligencja] Autorzy: Wenqing Peng, Michael Boy, Zhi-Song Liu Atmospheric chemical mechanisms are commonly distributed in the language of the Kinetic PreProcessor (KPP), which generates efficient Fortran or C code but does not fit into the differentiable programming frameworks in which machine-learning models are developed. We present KPPax, a kinetic preprocessor that generates differentiable, just-in-time compiled, and vectorisable chemistry code in JAX from mechanisms written in the KPP language. KPPax evaluates the rate law with sparse operations in log space, which keeps it differentiable, and integrates the stiff system with the implicit solvers and the forward- and reverse-mode adjoints of the \texttt{diffrax} library, so that exact sensitivities are obtained without hand-derived adjoint code. We demonstrate two applications with the POLLU benchmark mechanism. In the first, the Fisher information matrix computed from an automatically differ…
-
Can LLMs Uncover Hidden Physical Laws through Free Exploration?
[Przetwarzanie języka] Autorzy: Zhen Yang, Wen Wang, Xander Xu i 1 więcej Scientific discovery often begins with an unexpected observation that prompts a new research question. In a world with altered physical laws, can large language models (LLMs) notice unexpected behavior, such as heavier objects falling more slowly, and discover the law through experiments without being told what to investigate? To evaluate this ability, we introduce LongChang, an automated framework that creates simulated worlds with altered physics, where one or more laws differ from ordinary physics. The evaluated LLMs act as explorers, manipulating objects and building tools to investigate their own questions without research tasks or hints about these laws. Separate LLM agents generate and review scenes, review tool designs, and evaluate reports for correctness and experimental support using the altered physical laws and exploration records. These records guide scene evolution for fu…
-
MuonGS: Pretraining LLMs with Relaxed Weight-Norm Control
[Uczenie maszynowe] Autorzy: Athanasios Glentis, Dawei Li, Mingyi Hong Weight decay and explicit weight-norm constraints improve optimizer performance in language model pretraining, yet a unified understanding of why such control helps and how much is needed remains incomplete. We analyze norm control in Muon over the entire training trajectory using the \emph{accumulated effective learning rate}, $C_T=\sum_{t<T}η_t/\|W_t\|_F$, where $η_t$ is the nominal learning rate and $η_t/\|W_t\|_F$ is the effective learning rate relative to the weight norm. For bounded update directions, accumulation over any training interval bounds relative weight displacement. We show that vanilla Muon can accumulate only logarithmically, potentially limiting exploration and helping explain its slower empirical progress, whereas MuonW and MuonH guarantee at least linear accumulation under the stated conditions. Going beyond bounded-norm control, we show that sufficiently slow norm…
-
Classical Verification of Quantum Computation Beyond the Polynomial Hierarchy
[quant-ph] Autorzy: Atul Mantri It is not known whether a classical polynomial-time verifier can verify arbitrary polynomial-time quantum computations with an efficient quantum honest prover without computational assumptions. We show that, relative to a classical oracle, such verification is possible for a language beyond the polynomial hierarchy that is decided exactly in quantum polynomial time. The protocol is public-coin, with perfect completeness and soundness error at most 1/4. To our knowledge, no language with such a proof system was previously proved to lie outside AM relative to an oracle. For every unbounded polynomial-time computable function, the oracle can be chosen so that the message count and the oracle query counts of the quantum algorithm, verifier, and honest prover are bounded by this function of the input length. The message count is optimal up to a constant factor, since for a suitable oracle ev…
-
What Improves During Pretraining? Tracking Knowledge Acquisition with Point-in-Time Models
[Sztuczna inteligencja] Autorzy: Chang Su, Bin Wu, Emine Yilmaz i 1 więcej Language models pretrained on web corpora collected over multiple years learn both general and domain-specific knowledge. How these different kinds of knowledge are learned as pretraining progresses remains unclear. Recent point-in-time models trained on web snapshots from different years provide a way to probe how knowledge prevalence varies over time. Using these models, we propose a temporal variability score (TVS), defined as the coefficient of variation of an item's negative log-likelihood across models. A higher score suggests that the knowledge may be less consistently represented across years of web text. We evaluate six benchmarks covering diverse topics using six models from multiple open-source model families. We find that low- and high-TVS items are learned similarly early in training, but high-TVS items improve faster later on. At the end of the pretraining run, high-TVS it…
-
Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions
[Sztuczna inteligencja] Autorzy: Anouar Imel, Imad Charradi, Abderrahman Sghir i 1 więcej When an LLM group's discussion is compressed into a short memory for a final decision maker, what should the memory keep? Two natural heuristics keep the rarest claims or the claims relevant to the decision criteria. On hidden-profile tasks both look attractive, because how widely a fact is held is confounded with whether it helps. We introduce CrossProfile, a diagnostic benchmark of 60 templates with automatically verified answer keys, in which the ownership of supporting, decoy, and irrelevant facts is crossed while their text is held fixed (480 tasks). Across Qwen2.5-7B, Llama-3.1-8B, and two DeepSeek models, both heuristics fail in predictable places. Selecting by relevance readmits decoys, because decoys are on topic: even a perfect relevance filter loses 23 to 31 points to rarest-first selection in the classic hidden-profile configuration. Rarest-first selection is no better than …
-
VideoLVR: Latent Visual Reasoning over Grounded Video Evidence
[Widzenie komputerowe] Autorzy: Shilong Li, Xingyuan Bu, Hao Shi i 4 więcej Chain-of-thought reasoning has substantially advanced video understanding in multimodal large language models (MLLMs). However, language-based reasoning traces do not provide a reliable mechanism for models to revisit relevant visual evidence, leading to visual forgetting and impairing their ability to reason over video content. Existing approaches maintain visual grounding during reasoning in two main ways: they either refer to evidence using textual coordinates, which specify symbolic locations rather than the visual content itself, or reinsert cropped regions or frames into the multimodal context, preserving visual details at the cost of substantial context expansion. To address these limitations, we introduce VideoLVR, which constructs latent visual evidence from local regions at relevant video moments, thereby providing visual support for intermediate reasoning steps. To supervise …
-
Beyond Answer Changes: Matched Same-Class Controls for Local Audio Evidence
[cs.SD] Autorzy: Yunuo Wang, Maoyuan Chen, Yuanjin Huang i 1 więcej For audio-language models, an answer change after a local sound-event edit can reflect a response to the event's class, sensitivity to waveform rewriting, or both. We compare matched same-class and different-class replacements of a queried event. Both use the same interval, level estimate, donor fitting, and crossfade, while the same-class replacement preserves the correct answer. Across 600 synthetic soundscapes and three models from two architecture families, different-class replacements produce 49.7 to 60.9 percentage points more answer changes than same-class replacements. Same-class accuracy remains within 5.2 percentage points of original accuracy. Among trials with correct original and same-class answers, soundscape-weighted selective accuracy for the inserted class is 73.7 to 81.9%, averaging eligible trials within each soundscape and then weighting eligible soundscapes equally.…
-
MoI-Bench: A Benchmark for Image Generation and Editing on Mobile Devices
[Widzenie komputerowe] Autorzy: Kailai Feng, Haoxiang Rao, Yuxiang Wei i 5 więcej Developing on-device image models requires considering practical user needs, task types and device resource constraints. However, existing benchmarks provide limited guidance on identifying capability gaps between on-device models and server-side models. We introduce MoI-Bench, a benchmark grounded in mobile user needs, comprising 64 subtasks and 1150 samples. It defines 16 operations, such as removal and replacement, and eight visual target categories covering content such as portraits and text. These form two orthogonal axes whose applicable combinations define specific tasks, such as removing facial makeup. To better guide model improvement, we further propose MoI-Eval, which introduces task-specific criteria covering instruction following, visual quality and detail preservation. We further construct sample-level evaluation questions and aggregate their scores into overall quality an…
-
GAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting
[Uczenie maszynowe] Autorzy: Joseph Natter, Long Vu, Yifan Zhang i 3 więcej Traffic forecasting requires modeling complex temporal dynamics and the spatial dependencies imposed by road topology. Supervised graph-based models achieve strong performance, but are often trained for a particular dataset and sensor graph, making deployment to new or evolving networks costly. Prior-Data Fitted Networks (PFNs) offer a zero-shot alternative by learning in-context inference from synthetic task priors, which provide an explicit mechanism for encoding domain-specific assumptions. Existing forecasting PFNs, however, do not explicitly represent the graph-structured dependencies governing traffic dynamics. To combine graph-aware traffic modeling with zero-shot adaptation, we introduce the Graph-Aware Spatiotemporal Prior-Data Fitted Network (GAS-PFN). GAS-PFN incorporates sampled road topology into its synthetic task prior through random-walk diffusion, teaching the model to …
-
Understanding the limits of latent world models
[Uczenie maszynowe] Autorzy: Rodrigo Gonzalez Laiz, Steffen Schneider World models are widely proposed as core components for enabling agents to reason over long temporal and spatial horizons. Yet current evaluations often emphasize task performance while providing limited insight into whether learned world models acquire predictive latent dynamics that reflect the underlying structure of the environment. Here we introduce the concept of faithful latent world models as an equivariance condition between the environment's transition map and the learned latent dynamics. We propose latent rollout consistency (LRC) as a metric to evaluate action-conditioned latent prediction. Strikingly, we find that across the studied state of the art latent world models, none solves the task by actually faithfully modeling the dynamics of the environment.
-
Timestral
[Sztuczna inteligencja] Autorzy: Adrien Petralia, Alexandre Gavaudan, Artjom Joosen i 353 więcej We introduce Timestral, a family of four time series foundation models for probabilistic forecasting, with 5M, 28M, 123M, and 209M parameters. Timestral sets a new state of the art on GIFT-Eval, TIME, and fev-bench, where Timestral-209M and Timestral-123M take the top two places on every metric. We achieve this with three ingredients: Decoupled Horizon Forecasting (DHF), which separates prediction tokens from the causally encoded context, so that longer horizons are trained without masking context and each observed value is both a forecast target and context for later forecasts; a covariate framework that natively supports known-future covariates within a causal architecture; and a two-stage pipeline that pretrains exclusively on a diverse, large-scale synthetic corpus before post-training on a mix of real and synthetic data with extended context. This report describes the model design …
-
REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation
[cs.IR] Autorzy: Yuxi Huang, Silin Zhou, Chenhao Wang i 5 więcej Personalized recommendation depends on learning semantic and collaborative relations among items from online content and user interactions. Generative recommendation (GR) offers a promising paradigm by autoregressively generating discrete semantic IDs (SIDs) of items. However, randomly initialized SID token embeddings and GR models trained from scratch do not directly inherit the semantic relations inherent in items, while inter-item collaborative relations are learned largely implicitly through token-level attention and next-token supervision. To address this limitation, we propose REGER, a unified framework that explicitly incorporates inter-item relations into semantic pretraining, history encoding, and SID generation. We pretrain the GR model through generative semantic retrieval, enabling it to inherit inter-item semantic similarity by learning to generate semantic neighbors' SIDs.…
-
TeamGym: A Gym for Team Decision-Making by AI Agents with Distributed Information
[Sztuczna inteligencja] Autorzy: Chanwoo Park, Jaywoong Jeong, Zachary Wojtowicz i 4 więcej Many real-world decisions require teams to integrate information distributed across participants. Yet AI agents are still primarily trained and benchmarked in isolation. We introduce TeamGym, an environment for evaluating and training language model-based agents on team decision-making problems constructed from real-world legal, finance, medical, and software engineering corpora. TeamGym introduces a method to identify a minimal set of facts, each element of which is necessary and all of which are collectively sufficient for a correct final decision, which we call pivotal information. This enables TeamGym to both control the distribution of pivotal information and track how well agents identify and integrate pivotal information when making team decisions. Examining 8 language models on 12 source corpora, we find that current AI agents often fail to effectively share information: Distrib…
-
Gym-Anything-RT: Scaling Real-Time Environments for Vision-Language Agents
[Uczenie maszynowe] Autorzy: Pranjal Aggarwal, Sean Welleck AI agents have made substantial progress in domains where they have a non-trivial amount of time to deliberate between actions, such as mathematics, software engineering, and performing tasks on desktop applications. It is less clear how such models fare in settings that demand real-time interaction, such as playing a video game or operating a physical device. In these settings, the environment state may evolve as the agent is reasoning, or even as the underlying model is performing a forward pass. To gain insight into the real-time interaction capabilities of vision-language agents, we introduce Gym-Anything-RT. Our key idea is to construct visual minigames that demand a portfolio of capabilities required for interactive real-time settings. Gym-Anything-RT uses an agentic pipeline to automatically generate such environments based on a taxonomy of six capabilities required for real-time…