Search: “LONGSTREAM”

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control

PhysStream enables mid-generation interactive control of physics-grounded video via structured scene memory and velocity-increment signals, reducing motion distribution distance 33%.

PhysStream is an autoregressive physics-grounded image-to-video model that maintains structured scene memory—positional maps and object tracking maps derived online from previously generated frames—and accepts fine-grained motion control via sparse velocity-increment signals encoding physical quantities. Training runs in two stages: a bidirectional model finetuned with motion-control conditioning, then a causal autoregressive model with structured scene memory. It supports interactive mid-generation control over multi-object tabletop rigid-body scenes, reducing motion distribution distance (FVMD) by 33% and trajectory error by 12% over the strongest baselines. Human evaluators preferred it in over 85% of in-the-wild comparisons.

Hugging Face daily papers·updated Sep 15, 17:55 UTC · 20h ago·first Sep 14, 20:00 UTC · 1d agoAI research 2 sources

28

Google researchers uncover criminal zero-day exploit likely built with AI

Google links a likely LLM-built criminal zero-day for an open-source admin tool to planned mass exploitation and maps AI-assisted threats.

Google Threat Intelligence Group linked a zero-day exploit for a popular open-source web-based administration tool, enabling 2FA bypass with valid credentials via a semantic logic error, to a criminal group, citing educational docstrings, a hallucinated CVSS score, and textbook Python as signs of LLM authorship; the vendor was notified before a planned mass exploitation campaign. The report also details Russia-nexus malware families CANFAIL and LONGSTREAM using AI-generated decoy code, the PROMPTSPY Android backdoor driving the UI through the Gemini API, APT27 using Gemini to build relay tooling, and the TeamPCP (UNC6780) supply chain compromise of LiteLLM and Trivy repositories that planted the SANDCLOCK credential stealer.

Help Net Security·Aug 24, 04:21 UTC · 23d agoThreat actor

78

ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding

ShallowStream builds streaming-video retrieval indexes from shallow MLLM layers, cutting per-frame prefill latency by up to 52.1x.

ShallowStream is a framework for streaming video understanding with multimodal LLMs that uses the model's shallow layers to simultaneously encode frames and maintain an always-on lightweight retrieval index via shallow-layer KV caches, avoiding full-depth prefill for every incoming frame. At query time, shallow-layer attention scores plus a diversity-aware selection strategy retrieve relevant context frames. It reports performance on par with the strongest existing streaming methods while reducing per-frame prefill latency by up to 52.1x and 10-second end-to-end latency by up to 11.9x, with code released on GitHub.

Hugging Face daily papers·Sep 1, 20:00 UTC · 14d agoAI research

24

How Does mHC Use Its Residual Streams? Selective Routing and Near-Identity Mixing

Analysis of DeepSeek-V4-Flash shows four-stream mHC residual blocks use only about two streams effectively, with late-layer mixing providing little benefit.

The study examines the four-stream residual pathway of DeepSeek-V4-Flash, finding typical attention or FFN sites effectively use about two streams and that residual mixing is modest, occurring primarily in early layers. Replacing late mixers with identity increases C4 perplexity by only 1.9% while replacing early mixers raises it by 41%. Retaining the three largest routing weights per token increases perplexity by at most 2.7%, showing the model uses only part of the flexibility afforded by the four-stream design.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 16:02 UTC · 11d agoAI research

42

CVE-2026-16028: Protocol::HTTP2 versions before 1.14 for Perl allow memory exhaustion via closed streams that stream_state never removes from the connection stream table

CVE-2026-16028: Protocol::HTTP2 Perl library before 1.14 lets closed streams linger in the connection table, enabling remote memory exhaustion.

Protocol::HTTP2 versions before 1.14 for Perl allow memory exhaustion because closed streams are never removed from the connection stream table by stream_state. The flaw was disclosed on oss-security by Robert Rothenberg on September 7, 2026. Users should upgrade to Protocol-HTTP2 1.14 or later on CPAN.

oss-security·Sep 7, 18:45 UTC · 8d agoVulnerabilityCVE-2026-16028

28

WireGuard-Linux Stack-Based Buffer Overflow in lsiio (Linux IIO Userspace Tool) Due to Unbounded fscanf

The Linux IIO userspace tool lsiio has a stack buffer overflow in find_type_by_name() caused by unbounded fscanf reads of oversized filesystem-backed attribute values.

A stack-based buffer overflow exists in the Linux Industrial I/O (IIO) userspace utility lsiio. In the find_type_by_name() function, the program reads an unbounded string from a filesystem-backed attribute into a fixed-size stack buffer using fscanf("%s", ...). A crafted or oversized attribute value causes a write beyond the bounds of the destination buffer. Despite the title's reference to WireGuard-Linux, the flaw described is in the IIO lsiio utility.

Full Disclosure·Sep 4, 00:13 UTC · 12d agoVulnerability

12

ConvMem: Convolutional Memory for Long-Context Reasoning

Researchers propose ConvMem, a training-free framework treating LLMs as convolutional kernels for parallelizable long-context reasoning beyond fixed context windows.

ConvMem reformulates long-context reasoning as a hierarchical convolution in which the LLM summarizes text segments hierarchically, shortening the reasoning path from a linear chain to a logarithmic tree. It uses configurable strides, skip connections, and multi-kernel convolution to capture evidence, decompose queries, and enable massive parallelization across segments and reasoning threads. On RULER-HotpotQA and RULER-2WikiMultiHopQA it outperforms training-free baselines and avoids the out-of-distribution overfitting seen in RL-trained approaches like MemAgent.

arXiv cs.AI / cs.LG / cs.CL·Sep 9, 16:53 UTC · 6d agoAI research

38

PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents

PARSER uses parallel reader subagents and an RL-trained lead agent for long-context QA, beating baselines and cutting latency up to 11x.

The PARSER paper decouples reading from reasoning: frozen subagents each read one document chunk in parallel while an RL-optimized lead agent iteratively broadcasts queries and aggregates evidence in scatter-gather rounds. On multi-hop QA with 7K to 896K token contexts, a 4B-backbone PARSER beats the strongest sequential memory baseline by 5.7 points on average and 12.0 points at 896K tokens, and a 9B version surpasses DeepSeek-V4-Pro by 6.3 points. Controlled experiments show robustness to evidence position, order, and distance perturbations, with inference latency reduced by up to 11x.

Hugging Face daily papers·Sep 5, 20:00 UTC · 10d agoAI research1

52

Context Engineering Inside the Harness: 4 Mechanisms That Beat Context Overflow and Goal Loss on Long-Horizon Tasks

Survey of four harness mechanisms—context budgeting, compaction, todo-state, and memory—that keep long-horizon LLM agents on task across 200+ tool calls.

The article details how agent harnesses, not larger context windows, solve context overflow and goal loss on long-horizon tasks, citing Chroma's Context Rot report showing 18 LLMs (GPT-4.1, Claude 4, Gemini 2.5, Qwen3) degrade on long inputs. Concrete implementations include LangChain Deep Agents offloading tool responses over 20,000 tokens to the filesystem and truncating old tool calls at 85% window usage, and Claude Code capping auto memory at 25KB while re-reading the 5 most recently modified files after compaction. OpenAI's Responses API now offers server-side compaction via context_management with a standalone /responses/compact endpoint, which Codex uses for long-running coding tasks. Manus reports a roughly 100:1 input-to-output token ratio per ~50-tool-call task, motivating todo.md state recitation to prevent goal drift.

MarkTechPost·Sep 13, 05:56 UTC · 3d agoAI research1

52

VidaForge: Open Research Infrastructure for Video Pretraining Data Recipes

VidaForge releases open infrastructure and VIDAFORGE-3M (3.14M clips, 6,475 hours) linking video pretraining data recipes to downstream model performance.

VidaForge is an open research infrastructure that represents a video pretraining data recipe as an executable five-stage workflow from raw videos to training datasets. The team compares data recipes with different coverage and quality during early from-scratch pretraining of Wan 2.1 and V-JEPA 2.1, finding that broader-coverage recipes achieve the highest downstream benchmark scores while loss-based evaluation favors different recipes. They also release VIDAFORGE-3M, containing 3.14 million scene-level clips totaling 6,475 hours with fine-grained annotations and curation signals for video data-recipe research.

Hugging Face daily papers·Sep 5, 20:00 UTC · 10d agoAI research

22

Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model

Ambient team wins EgoLongQA 2026 sub-2B division by distilling an agentic long-video perception pipeline into a 2B vision-language model.

Ambient's entry to the EgoLongQA track of the Wearable-AI Challenge at ECCV 2026 placed first in the <=2B parameter division with 0.8279 on the held-out test set. The system distills the junior perception module of a tool-using agentic pipeline into a 2B student, reaching 89% of the pipeline's accuracy with 1.1% of its parameters and lifting a 27.1% base model to 81.4%. To meet the division limit, the multilingual embedding table is pruned from 248,320 to 143,469 rows, reaching 1.9985B parameters with provably identical logits on retained rows.

Hugging Face daily papers·Sep 9, 20:00 UTC · 6d agoAI research

35

[webapps] Langflow 1.8.4 - Path Traversal to Remote Code Execution

A path traversal to remote code execution exploit for Langflow 1.8.4, a popular LLM application builder, was published on Exploit-DB.

Exploit-DB lists a proof-of-concept exploit chaining path traversal to remote code execution in Langflow 1.8.4, an open-source tool used to build LLM applications and agents. The chain allows an attacker to write arbitrary files outside the intended directory and achieve code execution on the host. The provided text does not include a CVE identifier or reports of exploitation in the wild, but RCE in a widely deployed AI tooling product is notable for defenders.

Exploit-DB·Aug 31, 00:00 UTC · 16d agoExploit / PoC1

42

ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding

ReactVAU is a slow-fast streaming framework for real-time video anomaly understanding that reserves heavyweight MLLM reasoning for suspicious events, improving efficiency.

ReactVAU addresses causal streaming video anomaly understanding with three components: a lightweight Fast Detection Module using Spatial Grid Folding, Anomaly-Aware Persistent Memory that protects critical visual cues from temporal decay, and a Slow Reasoning Module activated only on suspicious events. This design minimizes heavyweight MLLM invocations during long normal intervals. Experiments show competitive anomaly detection and causal reasoning under strict streaming constraints with significantly enhanced computational efficiency.

Hugging Face daily papers·Sep 6, 20:00 UTC · 9d agoAI research

24

VU#308749: Remote Code Execution and Arbitrary File Read Vulnerabilities in Kaltura Servers

Insecure deserialization in Kaltura's legacy HTML5 Player V2 (mwEmbed) allows arbitrary file read and remote code execution; Player V7 is unaffected.

CERT/CC issued VU#308749 for two flaws in Kaltura's HTML5 Player V2 library (mwEmbed/html5lib), both caused by the same insecure deserialization bug. The flaws enable arbitrary file read and remote code execution via the exposed mwEmbedLoader.php endpoint. Affected versions include html5lib v2.45, v2.103 and earlier, and other v2.x releases; the currently supported Player V7 is unaffected. No evidence of exploitation was cited.

CERT/CC Vulnerability Notes·Aug 25, 16:11 UTC · 21d agoVulnerability

50

llm 0.34

Version 0.34 of Simon Willison's llm CLI adds response-duration metrics to log output, plus bug fixes and faster log querying.

The open-source llm command-line tool for interacting with large language models released version 0.34. The headline change adds response duration in milliseconds and human-readable form to llm logs --usage Markdown output, plus a new duration_ms field in llm logs --short. The release includes several contributed bug fixes and a significant performance improvement to llm logs, alongside the related llm-openrouter 0.7.1 release.

Simon Willison·Sep 2, 19:23 UTC · 13d agoAI tools & infra1

28

Multi-Grid Post-Training for Long-Form Multi-Shot Video Generation

MovieGrid arranges long videos on spatial grids during post-training, generating 6.05x more shots than temporal packing with state-of-the-art cross-shot consistency.

MovieGrid is a multi-grid post-training paradigm that decomposes long videos into temporally ordered chunks arranged on a spatial grid for joint modeling, enabling cross-chunk information exchange. The authors build the Multi-Grid Long Video (MGLV) dataset from 1,000 long-form videos, producing 54K grid videos paired with character-aware story prompts. Under the same token budget, MovieGrid generates 6.05x more shots than Temporal Packing in a 1,616-frame video. It achieves state-of-the-art intra-shot consistency of 0.9131 versus 0.8086 for HoloCine and inter-shot consistency of 0.5914 versus 0.5384 for StoryMem.

Hugging Face daily papers·Sep 5, 20:00 UTC · 10d agoAI research

20

Homebrew 7.0.0 Adds Built-In Vulnerability Scanner and Stronger Package Sandboxing

Homebrew 7.0.0 ships a native brew vulns scanner, OSV-backed advisory database, stronger sandboxing, and fixes a sandbox-escape issue.

Homebrew 7.0.0 introduces a built-in 'brew vulns' command that scans installed formulae, dependencies, and Brewfiles against a new Homebrew-specific advisory database and OSV.dev data, distinguishing backported fixes from outdated versions. The release hardens sandboxing by blocking home-directory reads during builds, disabling network access at install time, and replacing Bubblewrap with Landlock on Linux. It also fixes moderate-severity GHSA-5263-whxq-77hp, where a malicious cask could execute code outside the macOS sandbox via LaunchServices, and drops macOS Catalina while moving Intel Macs to Tier 3.

Cyber Security News·Sep 15, 13:55 UTC · 1d agoTools

35

[AINews] Fal’s H3 Max Live breaks the infinite videogen barrier

Fal post-trained MiniMax H3 into a 'Max' variant with 35x-faster inference, enabling faster-than-realtime AI video generation and infinite streams.

Fal post-trained MiniMax's H3 model into a 'Max' variant and optimized it for its in-house inference engine, achieving roughly 35x the speed of the official endpoint. The optimization enables faster-than-realtime video generation, demonstrated by an infinite interactive AI-generated stream productized by levels.io. The roundup also notes Meta Muse Code's general availability with an SDK, open DeepSeek-V4-Flash-Vision-Exp weights, GLM-5.3-Flash's strong agentic cost/performance rankings, and Tencent's 770B-parameter Hy4 Preview MoE with 49B active parameters.

Latent Space·Sep 1, 04:36 UTC · 15d agoAI industry

50

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

NVIDIA researchers detail an end-to-end system for online draft co-training that speeds speculative decoding in large-scale long-context RL post-training.

The paper tackles scaling online draft co-training for speculative decoding in RL post-training, where rollout generation dominates cost. It extends packed, load-balanced zigzag ring attention to merge rank-local branch attention with causal main-sequence attention for context parallelism, and introduces TapChannel to transport target features across pipeline-parallel stages without changing the schedule. Experiments show co-trained drafts tracking the policy baseline with substantial rollout and end-to-end speedups up to 122B parameters and strong scaling at 256K tokens.

Hugging Face daily papers·Sep 6, 20:00 UTC · 9d agoAI research

26

LACE: Layer-Wise Compression for Dynamic Frame Rate Codecs

LACE introduces layer-wise compression for dynamic frame rate audio codecs, cutting sequence lengths and speeding TTS inference while preserving quality.

LACE (Layer-Adaptive Codec Encoding) applies an independent compression step at each quantization layer of a neural audio codec, enabling layer-specific segmentation boundaries instead of shared ones. Union alignment and boundary anchor mechanisms keep durations consistent for downstream text-to-speech. On LibriTTS, LACE achieves a better rate-quality tradeoff than prior dynamic frame rate codecs and improves TTS inference efficiency at competitive synthesis quality. Code is released in the ESPnet3 codec recipe.

arXiv cs.AI / cs.LG / cs.CL·Sep 15, 17:46 UTC · 20h agoAI research1

15

Vulnerabilities fixed in libxml2-2.15.4

libxml2 2.15.4 fixes an out-of-bounds read in xmlregexp's NXT macro plus several integer overflow and parsing flaws.

libxml2 2.15.4 (released September 1, 2026) includes security fixes: an out-of-bounds read in the xmlregexp NXT macro, missing overflow checks in dict.c, uri.c, and valid.c, an integer overflow in xmlIO before the writecallback, and an overflow check in xmlXPtrEvalXPtrPart. The release also propagates parseFlags in xmlXIncludeProcess and xmlXIncludeProcessTree. No CVE identifiers, exploitation, or severity ratings are given in the announcement.

oss-security·Sep 4, 21:23 UTC · 11d agoVulnerability

28

Retrofitting Code Using LLMs to Support Exceptional Behavior

EXCODER combines static/dynamic analysis with LLMs to retrofit exception-handling code, achieving 85.92% pass@1 with Qwen 2.5 Coder 32B on Java benchmarks.

The paper introduces the task of retrofitting existing code with Exception Related Code (throw statements, guarding conditions, try/catch blocks) so that given Exceptional Behavior Tests pass. EXCODER performs context engineering by integrating static and dynamic program analysis output with LLMs; it was evaluated on a benchmark built from 304 methods across 75 GitHub Java projects. Combined with Qwen 2.5 Coder 32B, EXCODER achieves pass@1, 5, and 10 rates of 85.92%, 86.18%, and 86.51%, roughly 13 percentage points over baseline, and manual inspection reveals remaining limitations.

arXiv cs.AI / cs.LG / cs.CL·Sep 9, 16:18 UTC · 6d agoAI research1

25

When Models Edit Too Much: On the Fidelity of Minimal Code Edits

A 400-task BigCodeBench evaluation shows frontier LLMs widely over-edit code; a preservation instruction cuts excess edits and raises Pass@1 by 2.3 points.

Researchers built an evaluation framework from 400 BigCodeBench problems with injected AST-level corruptions, each with a known minimal patch, to measure over-editing in LLM code repair. Even strong models like GPT-5.5 produce unnecessarily large edits despite high Pass@1. Adding a preservation instruction reduced average excess Levenshtein distance from 0.195 to 0.131, cut added cognitive complexity by 26.6%, and raised Pass@1 by 2.3 points. Reinforcement learning post-training gave the best out-of-domain edit-fidelity trade-off, while supervised fine-tuning overfit to seen corruption patterns.

Hugging Face daily papers·Sep 2, 20:00 UTC · 13d agoAI research1

30

Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction

Grouped Value Attention stores grouped values and reconstructs content keys via a learned linear map, cutting KV-cache size about 45-47% versus GQA.

GVA stores only grouped values and reconstructs content keys with a learned linear map absorbed into the query at decode time, while a small shared decoupled RoPE channel preserves positional information via a separately cached positional key. At 350M parameters trained on 30B FineWeb-Edu tokens, the 16-dimensional positional variant scores 44.18 average accuracy across five tasks versus 44.36 for GQA and 43.88 for MLA. Custom decoding kernels are in development with an open-source release planned.

Hugging Face daily papers·Sep 7, 20:00 UTC · 8d agoAI research

42

A Princeton Researcher Proposes Recurrent Looped Transformer (RLT) that Carries Decoder State across Every Token, Fixing 96 Blocks per Token with Unbounded Temporal Depth

Princeton researcher Yifan Zhang proposes Recurrent Looped Transformer, carrying full decoder state across every token for unbounded temporal depth.

Yifan Zhang's technical report defines the Recurrent Looped Transformer (RLT), pairing a causal encoder with a recurrent decoder whose final output and layerwise sliding-window attention cache carry into every subsequent token with no prompt-response boundary reset. The reference configuration ties 48 encoder and 48 decoder layers, executing 96 logical blocks per token while the state path grows to 48t blocks after t tokens at fixed per-token compute. The report details RL replay contracts that rebuild all states under current parameters and exact prefix snapshots for multi-turn serving, but explicitly reports no measured efficiency, reasoning quality, or scaling results.

MarkTechPost·Sep 13, 17:02 UTC · 2d agoAI research1

40

A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware

OreoLook's three-layer Redis caching architecture cuts redundant LLM calls and embedding work for CPU-hosted web-search answer generation.

The paper describes a three-layer caching architecture for OreoLook (formerly lixSearch), an open-source LLM answer engine: a Redis session context window with Huffman-compressed disk overflow, a semantic query cache matching rephrasings via embedding cosine similarity, and a URL embedding cache deduplicating embedding computations. Deployed on a single 8-vCPU Intel Cascade Lake server with 30 Hypercorn workers across three containerized replicas, it achieved an 89.3% aggregate Redis keyspace hit rate, 0.1 ms read latency, and 1.38 MB memory overhead. An LRU eviction daemon migrates idle sessions to disk and rehydrates them for resumption hours or days later.

Hugging Face daily papers·Aug 11, 20:00 UTC · Aug 11, 2026AI tools & infra1

34

BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference

BeaconKV introduces training-free KV cache compression using beacon queries, cutting long-reasoning inference memory up to 5.8x while preserving accuracy.

The paper shows recency-based KV cache compression assumptions fail in long-horizon reasoning because Thought Revisiting Tokens (TRT) re-attend to distant context such as early task-solving plans. TRT queries cluster into a small number of similarity groups, which BeaconKV exploits by maintaining compact beacon query representatives to anticipate revisited KV pairs without storing full query history. The training-free method achieves up to 5.8x memory reduction and over 4.3x throughput improvement across four open-source large reasoning models while nearly preserving full cache accuracy.

Hugging Face daily papers·Sep 3, 20:00 UTC · 12d agoAI research1

33

[AINews] DeepSeek v4.1-Flash: 763B-P8B-D16B novel causal Encoder–Decoder architecture with vision marks the Return of the Whale

DeepSeek released V4.1-Flash, an open-weight 763B-parameter model with a novel causal encoder-decoder architecture, 1M context, vision input, and MIT license.

DeepSeek launched V4.1-Flash, an open-weight MIT-licensed model using a novel causal encoder-decoder architecture with 763B total parameters and asymmetric active parameters: 8B for prefill and 16B for decode. It supports 1M-token context and text+image input, priced at $0.30 per 1M input and $1.20 per 1M output tokens with a 50% off-peak discount. Artificial Analysis scored it 40 on its Intelligence Index, above DeepSeek V4 Pro 0813, and Vals ranked it the #1 open-weight model ahead of Kimi K3. Baseten shipped day-0 support and Ollama began rolling it out to paid subscribers.

Latent Space·Sep 12, 05:56 UTC · 4d agoModel release 7 sources1

80

JustFit: 200K-Token LLM Serving on a 24 GiB Laptop with Just-in-Time State Management

JustFit MLX runtime serves 200K-token contexts for Qwen3.8-27B on a 24 GiB MacBook via just-in-time state management.

JustFit is an MLX-based inference runtime combining KVExec for compressed KV execution, PhaseSwap for component residency, and StateTrans for state-preserving serving transitions, independent of weight quantization. On a 24 GiB M4 Pro MacBook running Qwen3.8-27B MXFP4, it completed 196,608 input and 16,384 output tokens, raising single-request context from the mlx-vlm baseline's 30,720 positions to 212,992 (6.93x). Performance tests show 19.11 tokens/s on a 32K-input probe with a 16,374 MiB median peak footprint, and the runtime answered 29 of 30 AIME 2026 problems correctly.

arXiv cs.AI / cs.LG / cs.CL·Sep 15, 17:15 UTC · 20h agoAI research

38

Re: Vulnerabilities fixed in libxml2-2.15.4

libxml2 2.15.4 patches two flaws including a heap buffer overflow in xmlDictAddQString tracked as CVE-2026-86137 and CVE-2026-86138.

libxml2 releases before 2.15.4 are affected by an integer overflow in xmlDictAddQString in dict.c that leads to a heap-based buffer overflow, tracked as CVE-2026-86137 and CVE-2026-86138. The oss-security post from Debian's Salvatore Bonaccorso flags the fixed release for downstream tracking. No exploitation is mentioned in the disclosure.

oss-security·Sep 5, 12:16 UTC · 11d agoVulnerabilityCVE-2026-86137CVE-2026-86138

45