Search: “kv-cache”

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 · 9d agoAI research

Long-Lived Characters, Local Inference: Incremental Memory Maintenance for Game NPCs

Researchers present incremental KV-cache memory maintenance for long-lived game NPCs running locally on a quantized Qwen hybrid model.

The paper studies incremental memory maintenance for long-lived game NPCs deployed locally with a quantized Qwen hybrid recurrent-attention language model. The runtime removes superseded attention KV entries, computes replacement records at the true sequence tail, and preserves the continuing recurrent state and unchanged KV. Experiments across eight scripted maintenance rounds show true-tail updates preserve current-state and historical bindings, while slot-preserving alternatives repeat a double-subtraction error.

arXiv cs.AI / cs.LG / cs.CL·Sep 16, 17:09 UTC · 20h agoAI research

harshatheg/Qwen-2.5-1B-RLCD — new model trending #30 on Hugging Face

A community MLX inference engine evaluates constrained JSON schema fields in parallel on Apple Silicon, reporting 5.6-7.0x latency speedups with guaranteed schema validity.

The repository harshatheg/Qwen-2.5-1B-RLCD appeared at #30 on Hugging Face trending, but its content describes Parallel Constrained Decoding, an MLX-based inference engine for structured extraction and classification on Apple Silicon Macs. Benchmarked with mlx-community/Qwen2.5-1.5B-Instruct-4bit on an M4 Max, it reports 5.6x-7.0x latency reductions (e.g., 1,900 ms to 270 ms for a 28-field support triage task) with 100% syntactic validity and calibrated field-level probabilities. The engine prefills a single KV-cache, broadcasts it across all schema fields, and slices logits to valid candidate tokens for enum fields with up to 255 choices.

Hugging Face trending models·Sep 16, 01:35 UTC · 1d agoAI tools & infra1

[AINews] Andrew Ng gets into AI Engineering

Andrew Ng relaunches DeepLearning.AI around AI Engineering, defining four core skills from an analysis of 10,000+ job postings and expert interviews.

Andrew Ng, cofounder of Google Brain and Coursera, relaunched DeepLearning.AI with a focus on AI Engineering, basing the curriculum direction on an analysis of over 10,000 job postings plus interviews and surveys. He identifies four key skills: building and deploying AI applications, software engineering fundamentals, effective use of coding agents, and shaping the build with product sense. The Latent Space AI News issue also recaps agent ecosystem developments, including NVIDIA's 'Skill Lift' evaluation proposal showing skill scan scores correlate only weakly (Spearman rho = 0.14) with judged quality, and Konwinski's open-source persistent-agent 'microharness' Headlong, which achieved an unattended self-debugging repair in 48 minutes.

Latent Space·Aug 25, 02:50 UTC · 23d agoAI industry1

DeepSeek-v4.1 Flash: Pushing the Limits of KV Cache Compression

DeepSeek-V4.1 Flash is a 552B-parameter multimodal MoE model with 1M-token context achieving 4x KV cache compression for long-horizon agent workloads.

A detailed analysis of the DeepSeek-V4.1 Flash technical report describes a 552B-parameter multimodal mixture-of-experts model supporting contexts up to 1 million tokens. Its Causal Encoder-Decoder (CED) architecture activates 8B parameters during prefill and 16B during decode, and reportedly delivers about 420 tokens/s. Joint optimization of architecture (CSA2 cross-layer compression), FP4 KV cache precision, and deployment strategy cuts runtime KV cache to roughly 1/4 and persistent KV cache to about 1/8 of DeepSeek-V4-Flash at the same sequence length, targeting storage and bandwidth bottlenecks in long-horizon agent serving. The author notes all DeepSeek-V4 Pro models were taken offline following the release.

Hacker News · AI·01:39 UTC · 11h agoModel releaseHN 41↑ · 3 comments

Meet Redis LangCache: A Managed Semantic Cache That Cuts LLM API Costs by Up to 90% and Returns Cache Hits Up to 15x Faster

Redis launches LangCache, a managed semantic cache matching LLM prompts by meaning, cutting API costs up to 90% and returning hits up to 15x faster.

Redis LangCache is a fully managed semantic caching service in public preview on Redis Cloud, accessed via a REST API with Python and JavaScript SDKs. It embeds incoming prompts, vector-searches stored entries, and returns a cached response when similarity clears a configured threshold, skipping the LLM call entirely. Redis claims up to 90% cost savings and up to 15x faster cache hits; a demo run showed 0.37 seconds versus 2.232 seconds direct inference (about 6x) with zero LLM tokens. Customer Mangoes.ai reports a 70% hit rate, 70% lower LLM spend, and 4x faster responses on a patient-care voice app.

MarkTechPost·Sep 10, 22:34 UTC · 6d agoAI tools & infra1

Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses

Quesma benchmarks Qwen3.8 27B quantizations: 4-bit Q4_K_M matches BF16 on key benchmarks while 1-bit collapses to random chance.

Quesma spent roughly $3,000 on Modal GPUs testing Unsloth GGUF quantizations of Qwen3.8 27B across GPQA Diamond, IFBench, and Terminal-Bench 2.1. The 17 GB Q4_K_M quantization matched the 55 GB BF16 model on Terminal-Bench 2.1 and showed little degradation down to 4-bit, while the 2-bit UD-Q2_K_XL dropped noticeably. At 1-bit, scores on GPQA Diamond fell to random-guess levels, with longer reasoning making results worse, and reasoning effort settings significantly affected outcomes.

Hacker News · AI·Sep 8, 14:49 UTC · 8d agoAI researchHN 56↑ · 30 comments1

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 · 13d agoAI research1

New Deepseek model V4.1-Flash cuts memory needs for AI agents

DeepSeek released V4.1-Flash, a 552B-parameter open-weight model cutting KV cache needs to a quarter of its predecessor for cheaper million-token AI agents.

DeepSeek released V4.1-Flash, a multimodal model with 552 billion total parameters and 1 million-token context, trained from scratch on 45 trillion tokens of text and images. The model reduces KV cache footprint to about a quarter of DeepSeek-V4-Flash in fast GPU memory and one-eighth offloaded, and 437x smaller per token than DeepSeek-V1, via an encoder/decoder split, 8-16B active parameters per token, and FP4 cache storage. It scores 74.2% on DeepSWE v1.1, narrowly beating Anthropic Opus 5 and OpenAI GPT-5.6 Sol, with gains attributed to data and RL scaling rather than new algorithms. Weights are on Hugging Face under MIT license, also served via API at V4-Flash prices.

The Decoder·Sep 10, 12:40 UTC · 7d agoModel release1

[AINews] Poolside gets $12B reverse-execuhire to NVIDIA; founders stay for $1B, employees go for $6B, Infraco scaling to 7GW neocloud

NVIDIA struck a $12B deal with AI coding startup Poolside, licensing its Model Factory and hiring 109 of its technical employees.

NVIDIA spent roughly $12B in an unusual reverse-execuhire of Poolside, licensing the company's Model Factory while hiring 109 of its ~115 technical staff; founders retain a $1B stake and employees receive about $6B. Poolside had raced to raise $2B to fund a 40,000 GB300 cluster after missing a six-week funding window, and founders argue frontier-scale training now requires an order of magnitude more compute plus contracted data center space. An infrastructure arm spun out in January 2026 is scaling toward 7GW as a neocloud. The newsletter also recaps OpenAI and Anthropic agent-platform releases.

Latent Space·Aug 21, 05:45 UTC · 27d agoAI industry

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 & infra2

Speculative Decoding in vLLM on AMD GPUs

vLLM benchmarks speculative decoding on AMD Instinct MI300X and MI355X GPUs across five drafting methods including EAGLE-3 and native MTP.

The vLLM project documents draft-and-verify speculative decoding support for AMD GPUs via ROCm, comparing native MTP, Gemma 4 MTP, EAGLE-3, DFlash, and DSpark drafting approaches. Output-token throughput effects varied with drafting method, proposal length, model family, draft checkpoint, workload, and acceptance behavior. The post also covers how to enable each method plus practical tuning and observability considerations.

Hacker News · AI·Sep 7, 09:26 UTC · 10d agoAI tools & infraHN 141↑ · 52 comments1

Fathom: Per-Query Read Depth for Sparse Decoding over Offloaded KV Cachesnew

Fathom introduces per-query bit-depth scanning of offloaded 4-bit KV caches, making long-context decoding 1.67x faster on Qwen3-8B at one million tokens.

Fathom is a key-scan method for sparse attention over KV caches resident in host memory, where each query adaptively chooses how many bits of each key channel to read using reverse water-filling over variance-weighted channel importance. The 4-bit K cache is stored channel-major as bit planes, so reading a prefix of planes is an exact t-bit quantizer. At one million tokens on Qwen3-8B, decode steps are 1.67x faster in GPU time than 136-bit scans used by Double Sparsity, Loki, and SparQ r=32, and 92-bit scans match the accuracy of 136-bit scans on real coding-agent sessions. The method requires the index to be offloaded to host memory and matches exact top-k decoding on RULER-style tasks.

Hugging Face daily papers·Sep 14, 20:00 UTC · 2d agoAI research

Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra

Cognition released SWE-2, a coding model post-trained from Kimi K3 that scores 50.0% on FrontierCode 1.1 Main, near Fable 5.1 at 64% lower cost.

Cognition introduced SWE-2, its most advanced coding model, post-trained from the 2.8T-parameter Kimi K3 base model. It achieves 50.0% on FrontierCode 1.1 Main, 73.0% on DeepSWE 1.1, and 92.8% on Terminal-Bench 2.1, beating Grok 4.6 and SWE-1.7 while matching Fable 5.1 and GPT-5.6 Sol at a fraction of the price. The company says it scaled reinforcement learning to the multi-trillion-parameter regime for the first time, using Pareto-informed cost penalties that train all reasoning-effort levels in a single run, tripled RL environments, and NVFP4/FP8 quantization-aware training. SWE-2 is available today in Devin Desktop and CLI, with rollout on Devin Web and Fusion.

Hacker News · AI·updated Sep 12, 20:00 UTC · 4d ago·first Sep 10, 15:29 UTC · 6d agoModel release 7 sourcesHN 58↑ · 15 comments2

DeepSeek AI Released DeepSeek-V4.1-Flash with 1M Context, FP4 KV Cache, and Cross-Layer Attention Reuse

DeepSeek released open-weight V4.1-Flash, a 552B MoE model with 1M context and FP4 KV cache, beating Opus-5 and GPT-5.6 Sol on agent benchmarks.

DeepSeek-V4.1-Flash is a multimodal Mixture-of-Experts model with a 552B-parameter backbone plus 196B Engram parameters, activating 8B parameters at prefill and 16B at decode, with a 1M-token context window. It introduces a causal encoder-decoder design, Compressed Sparse Attention 2, and FP4 (E2M1) KV cache quantization, cutting global KV cache to 890 bytes per token, about 1/4 of V4-Flash and 437x smaller than V1. Pre-training covered 45T multimodal tokens; the MIT-licensed weights ship on Hugging Face with vLLM and SGLang support. It scores 90.6 on Terminal-Bench 2.1 and 74.2 on DeepSWE v1.1, ahead of Opus-5 and GPT-5.6 Sol.

MarkTechPost·Sep 10, 07:31 UTC · 7d agoModel release1

HyQuant: Hybrid-Precision Quantization for LLM Attention

HyQuant keeps most LLM attention states low-bit while preserving vertical-line tokens and local windows in high precision, maintaining near-lossless accuracy.

HyQuant is a hybrid-precision quantization framework for LLM attention that quantizes most attention states to low bits while keeping accuracy-critical vertical-line tokens and local-window states in full precision, selected via lightweight attention-pattern signals. In the prefill stage it uses a hybrid-precision attention operator, and in the decode stage it applies the same principle to KV-cache compression with fused dequantization and attention computation. Across diverse tasks, models, and datasets it maintains nearly lossless accuracy; code is available on GitHub.

Hugging Face daily papers·Aug 27, 20:00 UTC · 20d agoAI tools & infra1

Toolkit Hidden Inside Oracle Database Evades Endpoint Tools

Infosecurity Magazine·Aug 6, 15:30 UTC · Aug 6, 2026Vulnerability

Agnes-AI/Agnes-3.0-Flash — new model trending #30 on Hugging Face

Agnes AI releases open-weight Agnes-3.0-Flash Preview, a 33B multimodal model with 262k-token context under Apache 2.0.

Agnes AI released Agnes-3.0-Flash Preview, an open-weights multimodal checkpoint with 33B parameters and a 262,144-token context window under Apache 2.0. The model supports text, image, and video understanding, tool calling, and adjustable reasoning effort. The repo clarifies this preview checkpoint is distinct from the production/API Agnes 3.0 Flash model, which uses a different configuration with a 1M-token context window. Reported reference results include IFBench 74.20 and SciCode 38.08 against peers such as Qwen3.6-35B-A3B, Kimi K2.5, and MiniMax M3.

Hugging Face trending models·Sep 11, 15:50 UTC · 5d agoModel release

deepseek-ai/DeepSeek-V4.1-Flash — new model trending #28 on Hugging Face

DeepSeek releases DeepSeek-V4.1-Flash, a 552B-parameter multimodal MoE model with 1M-token context and KV cache cut to 890 bytes per token.

DeepSeek-V4.1-Flash is a multimodal Mixture-of-Experts model with a 552B-parameter backbone that activates 8B parameters per token during prefill and 16B during decode. It uses a Causal Encoder-Decoder architecture, Compressed Sparse Attention 2, and FP4 KV caching to reduce the global KV cache footprint to 890 bytes per token, roughly one quarter of DeepSeek-V4-Flash. The model was trained from scratch on 45T tokens with context extended to 1M tokens, includes an Engram conditional-memory module (196B parameters), and is released under the MIT license. Post-training uses SFT, RL, and on-policy distillation with large-scale automated synthesis of agentic tasks and a controllable reasoning effort setting from 1 to 100.

Hugging Face trending models·Sep 10, 02:17 UTC · 7d agoModel release1

The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Predictionnew

Edge0 streams 35B-parameter MoE inference from SSD on a 24GB machine at 20 tokens/s using a one-token-ahead prerouter, with framework and checkpoints open-sourced.

The paper (arXiv 2609.18063) presents Edge0, a streaming MoE inference engine whose per-layer prerouter predicts the next layer's expert routing one token ahead so SSD reads can be pre-staged with nothing dropped. An unmerged recovery LoRA trained on the student path compensates for quality lost to int4 quantization and routing replacement. On a single 24GB machine it serves a 35B MoE at 20 tok/s within 3GiB of peak active memory, within a few points of its fp16 teacher across five public benchmarks; framework, checkpoints, and adapters are open source.

Hugging Face daily papers·Sep 15, 20:00 UTC · 1d agoAI tools & infra

Better Vector Search for Long Documents: Chunking Inside Manticore Searchnew

Manticore Search added automatic document chunking for vector columns, lifting long-document recall@5 from 55.1% to 83.3% in its benchmarks.

Manticore Search introduced a chunk_strategy option for model-backed vector columns in CREATE TABLE, offering five strategies (truncate, mean, fixed, recursive, sentence) with tunable max_tokens, overlap_tokens, and max_chunks, eliminating external splitters and separate chunk tables. On its 189-page, ~298k-word manual, sentence chunking improved recall@5 from 55.1% to 83.3% and MRR from 0.44 to 0.70, at roughly 2.5x RAM and 4x ingest time. Documents still return as single results; queries are never chunked.

Hacker News · security·10:30 UTC · 2h agoAI tools & infraHN 31↑ · 1 comments

rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference

rMuscle, a caching-based inference framework for vision-language-action models, achieves 1.29-1.42x speedups on RTX 4090 and Jetson Thor while preserving success rates.

rMuscle is a real-time inference framework for Vision-Language-Action (VLA) models that exploits cross-execution similarity in repetitive robot tasks via a dual-phase muscle-memory cache. The Context Cache reuses visual-token outputs to reduce computation, while the Action Cache reuses neuron activation patterns to reduce weight accesses, with online recomputation and sliding-window retrieval keeping overhead low. It achieves 1.29-1.42x speedups on RTX 4090 and Jetson Thor across LIBERO, RoboTwin, and real-world manipulation tasks while maintaining original success rates.

arXiv cs.AI / cs.LG / cs.CL·Sep 16, 17:34 UTC · 19h agoAI tools & infra1

Notes on gotchas while migrating 35kb preprompts from Opus to self-hosted Ollama

Opinion piece urges migrating 35KB preprompts from Anthropic/OpenAI to self-hosted Ollama, citing session privacy risks and safety filters blocking security research.

The author documents gotchas migrating 35KB preprompts from Claude Opus to self-hosted Ollama, motivated by fears that frontier providers train on user sessions, citing the OpenAI Navier-Stokes controversy. The piece argues inference providers cannot audit their own retention or training pipelines and that only self-hosted hardware offers verifiable privacy. It also criticizes frontier safety filters for refusing vulnerability research tasks and calls for models that support exploitability testing in CI/CD pipelines.

Hacker News · AI·Sep 14, 13:59 UTC · 2d agoAI industryHN 41↑ · 13 comments1

PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving

PACE cuts perceived latency in retrieval-augmented dialogue serving via cascading routing and filler control, reaching 0.41s P95 under load.

PACE is a serving framework for retrieval-augmented dialogue that optimizes Perceived Time-to-First-Response (PTFR) under quality and cost constraints. It combines a load-adaptive cascading router, a joint path-filler controller, and volatility-aware cache admission, deployed on a humanoid-robot sales service. On 75k CarQA requests, the cascade halved pure-LLM P95 PTFR (0.29s vs 0.53s) and the adaptive controller reached 0.41s P95, 2.4x better than RAG at high load; filler calls dropped 94% and stale answers fell from 86% to 0%.

arXiv cs.AI / cs.LG / cs.CL·Sep 9, 16:02 UTC · 7d agoAI tools & infra

VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification

VDiff-Bench, a 1,756-question benchmark, shows multimodal LLMs struggle with fine-grained image-difference identification, scoring as low as 8.7% on low-level changes.

VDiff-Bench is a multiple-choice benchmark of 1,756 four-way questions over image pairs covering 10 change categories including position, motion, color, texture, OCR/text and illumination, with curated hard negatives. Evaluation of 11 state-of-the-art open- and closed-source MLLMs shows fine-grained visual comparison remains brittle: 7-8B-scale open-source models score 52.5-70.6% on semantic changes but only 8.7-33.3% on low-level changes like noise and texture. Notably, Grok 4.3 shows a sharp performance drop on noise and texture differences, falling behind large open-source models like Kimi K2.5 and K3.

Hugging Face daily papers·Sep 4, 20:00 UTC · 12d agoAI research

Attackers Compile khunt Inside Oracle to Turn SQL Injection Into Windows SYSTEM Access

The Hacker News·Aug 6, 09:19 UTC · Aug 6, 2026Vulnerability1

Prior Labs Releases TabPFN-3.5: A Tabular Foundation Model That Beats the Winning Otto Kaggle Solution With Default Settings

Prior Labs releases TabPFN-3.5, a 220M-parameter open-weights tabular foundation model that beats the 2015 Otto Kaggle winning score with default settings.

Prior Labs released TabPFN-3.5, a tabular foundation model that predicts in a single forward pass without per-dataset training or tuning. The base model grew from 53M to 220M parameters with a single multitask checkpoint, learned Fourier features, and in-context ECDF rank encodings. It scores 0.375 on the 2015 Otto Kaggle private leaderboard versus the winning 0.382 and claims first place on seven tabular benchmarks including TabArena and BeyondArena. Open weights cover the base, Fast (84M), and Thinking variants, but production use requires the Prior Labs API or a commercial license.

MarkTechPost·Sep 16, 06:52 UTC · 1d agoModel release1

Molecular Déjà Vu: Digit-Level Retrieval of Published Values in Frontier Language Models

Audit of 22 frontier models finds widespread verbatim retrieval of published molecular property values, with higher reasoning increasing recall of memorized numbers.

An arXiv audit tests 22 frontier LLMs across 12 molecular regression benchmarks for verbatim retrieval of published values. More than 50% of the LLMs show verbatim retrieval on five datasets, and identical experiments are flagged 89% more often at a high reasoning level than at the lowest one. Suppressing retrieval moves model prediction errors closer together in relative terms, suggesting predictive capability is not determined solely by memorized values.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 17:32 UTC · 12d agoAI research1

ReMoMask-2: Latent Retrieval-Augmented Masked Motion Generation

ReMoMask-2 rebuilds retrieval in the generator's latent space for text-to-motion generation, achieving lowest FID on KIT-ML and SnapMoGen.

ReMoMask-2 is a retrieval-augmented text-to-motion framework that constructs its retrieval database directly in the generator's pre-quantization latent space and aligns text queries through a distilled lightweight projector, eliminating the representation gap. The framework combines Hierarchical Bidirectional Momentum contrastive learning, Semantic Spatial-Temporal Attention, and Topology Structured Masking to handle hierarchical motion structure. The retriever achieves state-of-the-art accuracy, and ReMoMask-2 attains the lowest FID on KIT-ML and SnapMoGen, with a single mask-transformer stage outperforming the previous two-stage pipeline while delivering the fastest inference.

Hugging Face daily papers·Sep 7, 20:00 UTC · 9d agoAI research

Rare Not Random Using Token Efficiency for Secrets Scanning

Researcher proposes token efficiency (string length divided by BPE token count) as a better post-regex filter than entropy for secrets scanning, validated on CredData.

The post explores whether Byte-Pair Encoding tokenization can replace Shannon entropy as the primary filter for candidate secrets captured by regex in tools like Gitleaks. It defines 'token efficiency' as string length divided by token count under the cl100k_base tokenizer; secret-like strings such as GitHub tokens tokenize into many small tokens and score low, while natural text scores high. Evaluating labeled secrets from the CredData dataset shows a usable separation, with roughly 2.5 suggested as a minimum cutoff versus Gitleaks' 3.5 entropy threshold. The technique is positioned as a post-regex filtering step rather than a standalone detector.

Lobsters · security·Sep 12, 06:42 UTC · 5d agoResearch

Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models

Researchers introduce KoNA, a benchmark exposing vision-language models' failures at selective non-compliance, plus fine-tuning that improves refusal and abstention accuracy.

KoNA is a benchmark for evaluating selective non-compliance in vision-language models across five categories: False Premise, Visual Inaccessibility, Universal Unknown, Task Feasibility and Safety. It tests both query-level and component-level non-compliance using paired single and compound queries, and evaluations across diverse VLMs show models often fail to refuse, correct or abstain appropriately, with failures worsening on compound queries. Fine-tuning VLMs on KoNA examples substantially improves non-compliance accuracy while largely maintaining performance on fully answerable tasks.

Hugging Face daily papers·Sep 3, 20:00 UTC · 13d agoAI research1

North Korea-linked Hackers Hide a Backdoor Inside HAProxy

Rapid7 reports North Korea-linked hackers implanted a backdoor compiled into HAProxy at South Korean automotive and media firms, enabling covert C2 and credential theft.

Rapid7 documented a previously undocumented Linux toolkit hitting South Korean automotive and media organizations, centered on a backdoor compiled directly into victims' HAProxy 2.8.12. The 'ted backdoor' uses HAProxy's native filter API to intercept HTTP traffic, receive C2 commands hidden in requests to a fake image path, and erase all traces from logs and counters; the toolkit also trojanizes crond, agetty, atd, sshd, and polkitd, adds an SSH keylogger, and runs curlRAT with virtualization checks. It can inject scripts or replace page content for selected victims, turning the load balancer into a watering hole. Attribution sits at medium confidence toward North Korean state actors, with overlaps to APT37-linked infrastructure and a concurrent Lazarus campaign; the campaign's command domains have since gone dark.

Security Affairs·Sep 8, 09:11 UTC · 9d agoThreat actor in the wild1

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

Hugging Face published a tutorial on training and finetuning multi-vector embedding models using the Sentence Transformers library.

Hugging Face's blog walks through training and finetuning multi-vector embedding models with Sentence Transformers. Multi-vector approaches store multiple vectors per document to support late-interaction retrieval. The post is a practical guide for developers building retrieval pipelines with the library.

Hugging Face Blog·Aug 26, 00:00 UTC · 22d agoAI tools & infra1

Atlas: Efficient Verifiable Semantic Search

Atlas delivers zero-knowledge proofs for HNSW semantic search, verifying RAG retrieval in under a second on SIFT1M and 2.0 seconds at 100M vectors.

Atlas lets a search provider prove that a query was answered correctly against a committed HNSW index without revealing the index, addressing provider deviations like truncation or bias. It combines offline preprocessing, a fixed-size-state restructuring of HNSW with a correctness proof, and timestep-tagged batching of per-step arguments. The system proves queries in under a second on SIFT1M and 2.0 seconds at 100 million vectors while preserving plaintext HNSW recall, and proven retrieval maintains end-to-end RAG answer quality at lower cost than prior verifiable retrieval systems.

arXiv cs.CR·Sep 10, 17:30 UTC · 6d agoResearch4

New Ted Backdoor Hides Inside Victims' Own HAProxy Builds to Intercept Web Traffic

Rapid7 found a new backdoor, ted, compiled into trojanized HAProxy at two South Korean organizations, with medium-confidence attribution to North Korean actors.

Rapid7 documented a previously undocumented Linux toolkit named ted compiled into the HAProxy load balancer binaries of two South Korean organizations in the automotive and media sectors. The implant intercepts web traffic, serves altered pages only to filtered visitors, and hides C2 exchanges from backend logs and HAProxy statistics; a companion RAT, curlRAT, beacons on a default 12-hour schedule. The toolkit also trojanizes crond, sshd, agetty, atd, and polkitd binaries and sanitizes logs and bash history. Rapid7 attributes the activity with medium confidence to North Korean state-sponsored actors, with domain infrastructure overlapping APT37 listings in maltrail and delivery resembling the Operation SyncHole campaign.

The Hacker News·Sep 4, 14:51 UTC · 12d agoThreat actor in the wild

Evidence-Grounded Retrieval for Investigation Hunt Lead Generation from CTI Reports

AHLERT generates environment-aware threat hunting leads from CTI reports using ATT&CK-seeded knowledge graph retrieval, roughly doubling F1 over flat-RAG baselines.

The paper introduces AHLERT, a system that converts Cyber Threat Intelligence reports into structured, investigable hunt leads via hybrid dense retrieval with multi-hop traversal over an MITRE ATT&CK-seeded knowledge graph and ontology-grounded RAG constrained to the defender's assets. It is LLM-agnostic and evaluated on public CTI reports for well-known APTs across proprietary and open-weight models. Hybrid evidence retrieval with ontology grounding raises mean F1 from 0.44 to 0.85, and AHLERT attains the highest effectiveness score (~86.95%) versus off-the-shelf LLMs.

arXiv cs.CR·Sep 8, 14:21 UTC · 8d agoResearch

Attention Quantization for Tabular Foundation Models

FP8 quantization of attention queries, keys, and values speeds tabular foundation model inference up to 1.7x with no accuracy loss.

The paper develops an FP8 quantization strategy targeting attention calculations (queries, keys, values) in tabular foundation models, arguing attention matters more than weight or KV cache quantization given their differing size and serving patterns versus LLMs. Aligning quantization error between test rows and training rows proves crucial, since misalignment causes drastic accuracy drops. A Triton kernel using explicit FP8 matrix multiplication achieves up to 1.7x speedup over regular 16-bit kernels, with no relevant accuracy loss on TabPFN-v3 and TabICLv2 across TabArena and BeyondArena benchmarks.

arXiv cs.AI / cs.LG / cs.CL·Sep 11, 16:31 UTC · 5d agoAI research1