October 10 – 16, 2026
Saturday to Friday, Brasília time.
- 3,169pieces
- 874sources
- 49new models
- 9exploited vulnerabilities
- 40major incidents
The Week's Top Stories
What mattered most, each in its maker's or first source's words.
-
1
Gemini 4 Argon (gemini-4-argon) generally available (GA)
Gemini 4 Argon (gemini-4-argon) generally available (GA): Released Gemini 4 Argon (gemini-4-argon), our most capable model built for complex coding, agentic, math, and science tasks. For API changes, pricing, and migrati…
Also reported by Google Gemini · Google AI · Google DeepMind · Vercel · Netlify · Windsurf
-
2
Open Models have crossed a threshold
Open models like GLM-5 and MiniMax M2.7 now match closed frontier models on core agent tasks — file operations, tool use, and instruction following — at a fraction of the cost and latency. Here's what our evals show and…
-
3
What Your Search Tool Sends Your Coding Agent
Most dangerous docs aren't attacks. They're honest pages telling your agent to fetch something unpinned and run it. We measured how often six search tools pass them on.
-
4
Muse Wonder now available on AI Gateway
Muse Wonder from Meta is now available on AI Gateway. The model is designed for coding, long-running agents, and computer use. It can plan multi-step tasks, delegate work to sub-agents, and recover from errors as work pr…
-
5
LFM2.5-24B-A2B: Built for Fast On-Device Agents
LFM2.5-24B-A2B: an open-weight 24B reasoning model with 2B active parameters, built for fast, private on-device agents. Beats Qwen3.6-35B-A3B on LiveClaw.
-
6
Meta Models Now Available in AI Gateway
Meta’s Muse Spark and Muse Wonder models are now available through Netlify’s AI Gateway with zero configuration required. Choose muse-spark-1.1 for coding, computer use, and multimodal perception; muse-spark-1.2 for codi…
-
7
Agents in Production, Part 1: Build an Overnight AI Support Agent using Managed Agents
Build an AI support agent on DigitalOcean Harness Runtime that triages tickets and drafts replies, with human approval to send. Live run: 99 tickets, zero sent.
-
8
What’s new with Google Data Cloud
October 12 - October 16 Looker Data Apps are now in Preview to build and host interactive, agent-generated applications natively inside Looker Generated using natural language prompts, the Antigravity CLI, or Claude Code…
Security
Vulnerabilities newly known to be exploited (CISA), then the week's most relevant advisories.
- CVE-2026-104935: Ivanti Connect Secure Authentication Bypass by Spoofing Vulnerability
Ivanti Connect Secure contains an authentication bypass by spoofing vulnerability that allows a remote unauthenticated attacker to execute arbitrary commands.
- CVE-2026-96951: Microsoft Windows Command Injection Vulnerability
Microsoft Windows Shell contains a command injection vulnerability that allows an unauthorized attacker to bypass a security feature over a network.
- CVE-2026-105134: Ahsay AhsayCBS Command Injection Vulnerability
Ahsay AhsayCBS contains a command injection vulnerability that could allow a remote attacker to execute operating system commands via manipulation of the random parameter in the Replication Receiver component’s /rps/api/…
- CVE-2026-76519: Cisco Secure Email Gateway Relative Path Traversal Vulnerability
Cisco Secure Email Gateway contains a relative path traversal vulnerability that could allow an unauthenticated, remote attacker to write arbitrary files on the underlying operating system.
- CVE-2026-105133: Ahsay AhsayCBS Improper Authentication Vulnerability
Ahsay AhsayCBS contains an improper authentication vulnerability that could allow a remote attacker to bypass authentication via manipulation of the random parameter in the API component’s checkSysPwd function. This vuln…
- CVE-2026-0322: Palo Alto Networks PAN-OS Code Injection Vulnerability
Palo Alto Networks PAN-OS contains a code injection vulnerability that could allow an authenticated attacker with network access to execute arbitrary code with root privileges on the firewall.
- CVE-2026-21589: Atlassian Multiple Products Files or Directories Accessible to External Parties Vulnerability
Multiple Atlassian products (Bitbucket Data Center ,Confluence Data Center, Jira Service Management Data Center, Jira Software Data Center, Bamboo Data Center, Crowd Data Center, Crucible and Fisheye) contain a files or…
- CVE-2026-102764: BeyondTrust Remote Support Authentication Bypass by Spoofing Vulnerability
BeyondTrust Remote Support contains an authentication bypass by spoofing vulnerability that could allow a remote attacker to perform file operations on the appliance.
- CVE-2025-61624: Fortinet Multiple Products Path Traversal Vulnerability
FortiOS, FortiPAM, FortiProxy, and FortiSwitchManager contain a path traversal vulnerability that may allow an authenticated attacker with admin profile and at least read-write permissions to write or delete arbitrary fi…
- AI Agent Security: Best Practices for Safe Deployment
Six AI agent security best practices for teams running coding agents and MCP servers: limit what a compromised agent can reach and catch credential misuse.
- When LLM Gateways Go Wrong: Findings from LiteLLM
TL;DR; Our security assessment of LiteLLM (v1.77.7), a widely used open-source LLM gateway, uncovered multiple high-impact vulnerabilities (tracked as CVE-2026-35029, CVE-2026-59823) which have been resolved as of LiteLL…
- AI coding agents expose developer screenshots on GitHub repos
PixelLeak exposures included many sensitive documents, highlighting why inventories of what agents can reach and publish are needed.
- Auditing the auditor: Unmasking Apex Accelerator
REF8801 exposes how Apex Accelerator combines convincing Web3 services with malicious npm packages, attacker-controlled AI infrastructure, and cross-platform malware delivery.
- 2026-016: Critical Vulnerability in GitLab CE and EE
On 12 October 2026, GitLab released versions 19.4.2, 19.3.4 and 19.2.8 of GitLab Community Edition (CE) and Enterprise Edition (EE), fixing 24 security issues among which a critical vulnerability that could allow an unau…
Major Incidents
Outages the providers themselves rated major or critical.
- Service Disruption Impacting Chase connections
- Issues with spin up node in google asia-southeast1 region
- Email API messages rejected with gw_reject// injection_failed
- Increased build and deployment failures
- Low Code Automation - Builds is facing issues
- Model Performance or Availability Issue
- [INCIDENT] https://www.contentful.com/developers/docs/ is not working
- Low Code Automation - Builds is facing issues
- 2026-October-13 Service Incident
- Multiple US endpoints experiencing timeouts and latency
- Observability upload and Agent Simulations failures
- Terraform Runs Failing
- Issues with package downloads
- Astro UI and API are appearing offline for some users
- Grok Bot routines not triggering
- Unable to Access dbt Platform
- Bandwidth Local Market Impairment - 977 - Macomb, IL
- Ingestion Halted for EAP data in EU
- Docs.redhat.com - Outage Investigating
- Builds, deploys, and queued deploys are not starting in all regions
- Site Performance - Coinbase Website
- Projects are not loading
- [Major] Issue with Box Drive
- Bitbucket Cloud - Service Disruption
- Tempo Write Failures in prod-us-central-0
- Widespread feature degradation
- Radar SMS challenge failures for phone numbers in mainland China (+86)
- INC20000287
- Elevated search latency on documentation sites
- Delayed cache invalidation in the shared region AP South 1
- Bitbucket login is not available
- Elevated iOS submission error rates
- Errors publishing Zaps from Guided Templates with app approvals enabled
- Platform Wide Rolling Host Reboots
- Cloudflare Fedramp Dashboard and Access
- Fly-metrics.net Grafana Dashboard Outage
- Programmable Video service outage
- Issues accessing the Cloudinary web UI
- MMS Delivery Incident
- High error rate on 1Password.com
Releases
Major and minor versions only — no patches.
- Anthropic Python SDK 1.14.0: api, add executionidentity to Managed Agents agents
Features api: add execution_identity to Managed Agents agents api: add organization_type_not_supported error to spend limit lists api: add telemetry destination test endpoint api: add telemetry destinations to the Admin…
- Anthropic Python SDK 1.15.0: api, add betweentools to thinking types in model capabilities
Features api: add between_tools to thinking types in model capabilities api: add the speed parameter and usage.speed to Messages api: return a Console organization's usage-tier spend cap as a read-only spend limit Chores…
- google-cloud-sdk-v0.1.0
Features api: add execution_identity to Managed Agents agents client: add OpenTelemetry spans for API calls Chores include the license files in the published packages internal: strip @internal declarations from published…
- aws-sdk-v0.8.0
Features api: add execution_identity to Managed Agents agents client: add native support for OpenTelemetry tracing If your app registers a global tracer provider, the SDK will create spans with it after upgrading, and th…
- bedrock-sdk-v0.35.0
Features api: add execution_identity to Managed Agents agents client: add native support for OpenTelemetry tracing If your app registers a global tracer provider, the SDK will create spans with it after upgrading, and th…
- sdk-v0.135.0
Features api: add between_tools to thinking types in model capabilities api: add the speed parameter and usage.speed to Messages api: return a Console organization's usage-tier spend cap as a read-only spend limit Bug Fi…
- Python 3.10 end of life
Here am I floating 'round my tin can Far above the moon Planet Earth is blue And there's nothing I can do Five years in orbit. Mission complete.;)
- ComfyUI 0.40.0: [Server.py] Update CSP to allow blob, and data: by @S0yKaf in #15565
What's Changed [Server.py] Update CSP to allow blob: and data: by @S0yKaf in #15565 Add comfy_attention and AttentionTensorContainer support to rest of models by @comfyanonymous in #16806 Implement the asset export API l…
- ComfyUI 0.41.0: Add ImageSDRToHDR node. by @comfyanonymous in #16990
What's Changed Add ImageSDRToHDR node. by @comfyanonymous in #16990 feat: Add a core route for the default workflow (CORE-340) by @alexisrolland in #16956 Add ReferenceMultiLatent node. by @comfyanonymous in #17009 Disab…
- v16.2.0
Changelog: https://docs.cypress.io/app/references/changelog#16-2-0
- electron v44.8.0
Release Notes for v44.8.0 Features Added support for Notification action buttons on Linux. #54890 (Also in 45 ) Fixes Fixed mouse cursor missing over native dialogs in certain scenarios on Windows. #54987 Fixed net.fetch…
- electron v43.8.0
Release Notes for v43.8.0 Fixes Fixed a crash on Linux at startup or on theme change with GTK modules loaded. #55016 Fixed a crash when creating a framed window on Wayland in environments where GTK could not initialize.…
- Envoy 1.40.0: Summary of changes
Summary of changes Breaking changes build: Envoy has switched from WORKSPACE to bzlmod. The WORKSPACE file is removed; Envoy, the API and the docs are published as Bazel modules ( envoy, envoy_api, envoy-docs ). Downstre…
- Release v0.64.0
What's Changed refactor(a2a-server): implement V1 to V2 settings migration logic by @jvargassanchez-dot in #29450 fix(acp): bridge PromptResponse.usage and emit usage_update notifications ( #29389 ) by @elberthc-byte in…
- Google Gen AI SDK 2.30.0: Accumulate streaming continuation usage metadata and expose initialprompttokencount (b27f3cd)
2.30.0 (2026-10-13) Features Accumulate streaming continuation usage metadata and expose initial_prompt_token_count ( b27f3cd ) Add continuation_token to the Interactions interaction.status_update event. ( 02db4c5 ) Add…
- Google Gen AI SDK 2.31.0: interactions, Add gemini-4-argon to Model enum (8554b07)
2.31.0 (2026-10-14) Features interactions: Add gemini-4-argon to Model enum ( 8554b07 ) Bug Fixes Clear continuation state and preserve prompt feedback when continuation hop returns no candidates ( a0d809c ) Fix the func…
- Goose 1.55.0: AIgateway declarative provider #12528
Features AIgateway declarative provider #12528 Propagate W3C trace context from ACP prompts to MCP tool calls #12697 Surface provider x-request-id on responses and errors #12587 Honor supports_vision declared on custom p…
- Laravel 13.36.0: [12.x] Make the worker timed out exit code reachable by @kieranbrown in #61623
[12.x] Make the worker timed out exit code reachable by @kieranbrown in #61623 [12.x] Support named S3 credential providers and Cloud IAM disks by @kieranbrown in #61757 [12.x] Address query issues by @taylorotwell in #6…
- Laravel 12.70.0: [12.x] Address query issues by @taylorotwell in #61838
[12.x] Address query issues by @taylorotwell in #61838 [12.x] Backport EncodedParameter from #61610 by @mahdyaralipor in #61871 [12.x] Generate different cache file based on configured $echoFormat by @crynobone in #61822
- Laravel 13.37.0: [13.x] Fix race condition with jobs using both onOneServer() and withoutOverlapping() by @tanerkay in #62007
[13.x] Fix race condition with jobs using both onOneServer() and withoutOverlapping() by @tanerkay in #62007 [13.x] Respect faked Sleep in limiter block() timeout by @grzegorczykp in #62017 [13.x] Improve getForeignKeys…
- LiteLLM 1.105.0: Verify Docker Image Signature
Verify Docker Image Signature All LiteLLM Docker images are signed with cosign. Every release is signed with the same key introduced in commit 0112e53. Verify using the pinned commit hash (recommended): A commit hash is…
- 2026-10-14, Version 24.22.0 'Krypton' (LTS), @richardlau prepared by @aduh95
Notable Changes [ ddbf974b47 ] - (SEMVER-MINOR) crypto: add crypto.parsePKCS12() (Brian Muenzenmeyer) #65627 [ c162c68ff0 ] - (SEMVER-MINOR) crypto: add a generic MAC API (Filip Skokan) #65553 [ a4ab3d84d7 ] - (SEMVER-MI…
- 2026-10-14, Version 26.12.0 (Current), @richardlau
Notable Changes [ 1ebd6d3677 ] - (SEMVER-MINOR) doc,lib,src: throw on missing WebAssembly or RX support (Paolo Insogna) #66533 [ 7f1937d2b9 ] - (SEMVER-MINOR) http: add websocketMask() and websocketUnmask() (James M Snel…
- Open WebUI 0.12.0: Realtime voice calls. Administrators can now switch Call mode in the Voice calls section of Audio…
Added Realtime voice calls. Administrators can now switch Call mode in the Voice calls section of Audio settings from Standard to Realtime, so Voice mode talks through an OpenAI Realtime voice model (gpt-realtime-2.1-min…
- OpenAI Agents SDK 0.24.0: expose MCP annotations on converted tools (#5356) (75813f8)
0.24.0 (2026-10-15) Features expose MCP annotations on converted tools ( #5356 ) ( 75813f8 ) support run-wide tool exception formatting ( #5326 ) ( 8fd9a7c ) Bug Fixes batch OpenAI conversation session writes within the…
- OpenAI Codex 0.163.0: New Features
New Features Open /config to search preferences across categories, change supported settings immediately, and see which changes require a restart. ( #52990, #53429 ) Send a follow-up while Codex is responding to steer it…
- OpenAI Node SDK 7.33.0: add browser and computer toolsets (1/4) (#2936) (3811840)
7.33.0 (2026-10-14) Features add browser and computer toolsets (1/4) ( #2936 ) ( 3811840 ) api: add beta session spending limits ( #2916 ) ( f57c965 ) api: add billing_not_active session error code ( #2911 ) ( ee3f743 )…
- OpenAI Node SDK 7.34.0: api, add regional processing residency options (#2942) (0f53768)
7.34.0 (2026-10-14) Features api: add regional processing residency options ( #2942 ) ( 0f53768 ) Bug Fixes deps-dev: bump @cloudflare/workers-types from 5.20260927.1 to 5.20261005.1 in /ecosystem-tests/cloudflare-worker…
- OpenAI Node SDK 7.35.0: api, add Decisions prompt caching options (#2956) (468b54e)
7.35.0 (2026-10-16) Features api: add Decisions prompt caching options ( #2956 ) ( 468b54e ) api: add prompt-based voice creation ( #2955 ) ( e9f788e ) api: add response error diagnostics and model notices ( #2948 ) ( 4f…
- OpenAI Node SDK 7.36.0: api, add safety identifiers to image requests and responses (#2957) (c95ccaf)
7.36.0 (2026-10-16) Features api: add safety identifiers to image requests and responses ( #2957 ) ( c95ccaf )
- OpenAI Python SDK 3.29.0: api, add billingnotactive session error code (#4052) (c88b320)
3.29.0 (2026-10-11) Features api: add billing_not_active session error code ( #4052 ) ( c88b320 ) api: add shida to named Live voices ( #4053 ) ( 7352cf5 ) api: add vault updates and metadata filters ( #4047 ) ( e72f493…
- OpenAI Python SDK 3.30.0: api, add beta session spending limits (#4058) (b570279)
3.30.0 (2026-10-14) Features api: add beta session spending limits ( #4058 ) ( b570279 ) api: add OCI external-storage provider support ( #4060 ) ( 9eb83fe ) api: add organization Decisions usage reporting ( #4062 ) ( 5e…
- OpenAI Python SDK 3.31.0: add browser and computer toolsets (1/4) (#4073) (47b9e4e)
3.31.0 (2026-10-14) Features add browser and computer toolsets (1/4) ( #4073 ) ( 47b9e4e )
- OpenAI Python SDK 3.32.0: api, add cache settings and key options [2/2] (#4087) (325da45)
3.32.0 (2026-10-16) Features api: add cache settings and key options [2/2] ( #4087 ) ( 325da45 ) api: add prompt-based voice creation ( #4091 ) ( 2e39db7 ) api: add regional processing residency options ( #4081 ) ( 21ce0…
- OpenAI Python SDK 3.33.0: api, add safety identifiers to image requests and responses (#4093) (c969e32)
3.33.0 (2026-10-16) Features api: add safety identifiers to image requests and responses ( #4093 ) ( c969e32 ) api: share Decisions cache breakpoint parameter type ( #4092 ) ( f7cefda )
- v1.69.0/v0.163.0
Images and binaries here: https://github.com/open-telemetry/opentelemetry-collector-releases/releases/tag/v0.163.0 End User Changelog Enhancements cmd/builder: Add dist.resource.detection.detectors to the builder config,…
- service/v0.163.0
Module set beta, Version v0.163.0
- oxlint v1.88.0
BREAKING CHANGES 7730e14 ast: [ BREAKING ] Refactor comment attachment storage ( #27512 ) (camc314) c904b61 ast: [ BREAKING ] Add comment attachment storage ( #27393 ) (camc314) Features bde9f69 oxlint/lsp: Show config e…
- oxfmt v0.73.0
BREAKING CHANGES 1ef2888 oxfmt: [ BREAKING ] Improve --migrate prettier ( #27444 ) (leaysgur) c2e6d5f formatter_toml: [ BREAKING ] Add oxc_formatter_toml crate wrapping oxc-toml ( #27365 ) (leaysgur) Features ce4e8dc oxf…
- sdk/v3.269.0: Make `pulumi watch` error by default (#25202)
pulumi watch now returns an error by default. This is the second step of the removal schedule in #24717. The error links the issue and tells users to set PULUMI_DISABLE_EXPERIMENTAL_WATCH_REMOVAL_ERROR=1 to run the comma…
- Revert "Freeze v3.269.0" (#25247)
Reverts #25245 Generated with Claude Code Co-authored-by: Claude Opus 5.5 noreply@anthropic.com
- pkg/v3.269.0: Changelog and go.mod updates for v3.269.0 (#25253)
Co-authored-by: github-actions github-actions@github.com
- Pulumi 3.270.0: [cli/env] Fix pulumi env edit, env set, env rm and env provider overwriting changes made after they read the…
3.270.0 (2026-10-16) Bug Fixes [cli/env] Fix pulumi env edit, env set, env rm and env provider overwriting changes made after they read the environment; on a conflict, env edit reopens the editor with your edits and the…
- pkg/v3.270.0: Changelog and go.mod updates for v3.270.0 (#25268)
Co-authored-by: github-actions github-actions@github.com
- React Native 0.88.0: C++, Add <React/FeatureFlags.h> umbrella header as the public entry point for react/featureflags (f970054a8a…
Added C++: Add <React/FeatureFlags.h> umbrella header as the public entry point for react/featureflags ( f970054a8a by @j-piasecki ) C++: Add <React/RendererBridging.h> umbrella header as the public entry point for react…
- swc_core@v82.1.0
chore: Publish crates with swc_core v82.1.0
- Supabase CLI 2.121.0: Supabase CLI v2.121.0 — 2026-10-14
Supabase CLI v2.121.0 — 2026-10-14 This release is mostly stack reliability fixes, plus new stack options and deprecation warnings you'll want to see before the next major version. Most entries below are from PR titles,…
- TRL 1.16.0: TRL now trains on AWS Trainium
Features TRL now trains on AWS Trainium The fused LM head from v1.15 is what made Neuron tractable; the remaining gaps are closed here. There is a guide to go with it. Neuron recompiles once per input shape, so an unpadd…
- Temporal 1.32.0-163.7: patched temporal version
patched temporal version
- Release v5.20.0
Release v5.20.0 New Model additions Muse Spark Open Muse Spark Open is a multimodal mixture-of-experts model from Meta that takes text, images, audio, and video as input and generates text. It has 816B total parameters (…
- gfx950-tutorial-v3.1
gfx950 tutorial pin v3.1: upstream main at b575c0c (PR #12229, the …
- 1.142.0
https://code.visualstudio.com/updates/v1_142
- camelcase v10.0.0
Breaking Require Node.js 22 27454cc Fixes Fix handling of letters outside the Basic Multilingual Plane ( 117) 92d7f63 Letters that need a surrogate pair (for example, Deseret and Osage) are now handled as one character.…
- @google/genai 2.29.0
[](https://www.npmjs.com/package/@google/genai) [](https://www.npmjs.com/package/@google/ge…
- openai 7.33.0
The official TypeScript library for the OpenAI API
- @anthropic-ai/sdk 0.134.0
The official TypeScript library for the Anthropic API
- openai 7.34.0
The official TypeScript library for the OpenAI API
- @google/genai 2.30.0
[](https://www.npmjs.com/package/@google/genai) [](https://www.npmjs.com/package/@google/ge…
- @anthropic-ai/sdk 0.135.0
The official TypeScript library for the Anthropic API
- openai 7.36.0
The official TypeScript library for the OpenAI API
- opencode 1.19.0: Run opencode upgrade --major to upgrade to OpenCode 2
Core Improvements Run opencode upgrade --major to upgrade to OpenCode 2. Bugfixes Allow the OpenAI ultrafast service tier. Validate PTY connection origins and tickets before checking whether a PTY exists. TUI Improvement…
- vscode-v1.0.0
fix(vscode): use the sst/opencode repository URL for Marketplace publ…
- pillow 13.0.0
https://pillow.readthedocs.io/en/stable/releasenotes/13.0.0.html Removals Remove undocumented GifImagePlugin. save netpbm 9901 [@akx] Remove ExifTags.IFD.Makernote 9850 [@radarhere] Drop support for Python 3.10 9750 [@hu…
- pnpm 12.12.0
This release shares task results and dependency builds through a remote cache, adds the addMissingPeerTypes setting, and lets pnpm add --config and pnpm update manage configuration dependencies. It also fixes dangerously…
- pnpm 12.13.0
This release adds the pnpm profile and pnpm token commands, the storeIndexFormat: files setting for stores shared over a network filesystem, and faster Python dependency resolution. Minor Changes Added the pnpm profile c…
- pnpm 12.14.0
This release adds the sideEffectsCache.exclude setting, stops pnpm install from waiting on the daily update check, and keeps pnpm from aborting with a core dump when the reader of its output exits. Minor Changes Added th…
- soupsieve 3.0
3.0 BREAK : :has() , by default, now behaves according to CSS more strictly, disallowing complex selectors that use combinators and prevents nesting :has() within :has() . This gives a safer, more performant default for…
- proto-v0.6.0
vllm-proto 0.6.0
- webpack 5.112.0: Minor Changes
Minor Changes Apply plugins set on a multi-configuration array to the MultiCompiler. (by @alexander-akait in #22702 ) Add optimization.minimize.css.dropOverriddenDeclarations, dropping a declaration a later one overrides…
Research
The papers most useful to a developer this week.
- BHunter: Generating Blind-Spot Driving Scenarios for Robustness Testing of Perception Systems
For widespread deployment of autonomous driving systems (ADS), perception robustness plays a fundamental role. However, maintaining robust perception performance remains a significant challenge, especially under occlusion-rich conditions, known as blind-spot driving scenarios. In…
- Distilling Transitional Patterns to Multimodal Large Language Models for Session-based Recommendation
Session-based recommendation (SBR) predicts the next item based on anonymous sessions. Traditional SBR explores user intents based on ID collaborations or auxiliary content. To further alleviate data sparsity and cold-start issues, recent Multimodal SBR (MSBR) methods utilize sim…
- Privacy Risks and Leakage Pathways in Agentic and Multi-Agent AI Systems
Agentic and multi-agent AI systems are increasingly deployed as part of operational systems, introducing autonomous planning, delegation, persistent memory, tool use, and inter-agent coordination into data-driven decision making. These architectural properties challenge prevailin…
- ChronoSteer: Bridging Large Language Model and Time Series Foundation Model via Synthetic Cross-Modal Alignment Dataset
Conventional forecasting methods are trained end-to-end on unimodal time series, which limits their ability to exploit textual information and undermines their generalization in data-scarce scenarios. Recently, large language models (LLMs) and time series foundation models (TSFMs…
- Exploring Backdoor Vulnerabilities and Fairness Challenges in Generative Models: A Survey
Global connectivity has increased societal diversity worldwide, fostering growth and dispelling negative stereotypes. However, ensuring equality remains challenging, with some groups favoured and others facing unequal opportunities. The evolution of Artificial Intelligence (AI) p…
End of the week.← The week before