30
60
An Open-Source End-to-End FHE Implementation for Privacy-Preserving Llama 3 8B Inference
Odin runs Llama-3-8B fully homomorphic encrypted inference on a single H100 in 366 seconds, a 4.51x speedup over THOR.
Odin is an open-source end-to-end GPU CKKS implementation for privacy-preserving Llama-3-8B inference that co-designs ciphertext packing with model execution. A feature-major cross-layer layout unifies residual connections and layer interfaces, while transient intra-operator layouts serve linear projections and attention, avoiding intermediate repacking of QK^T softmax outputs. Minimax polynomial approximation with input-range control reduces polynomial degree and multiplicative depth for nonlinear ops. With 128-token input, Odin evaluates all 32 Transformer layers on one NVIDIA H100 80 GB in 366.4 s using 58.9 GiB peak memory, versus 1651.9 s for the THOR baseline, a 4.51x speedup.
48
60
PuzzleMask: Abusing Plain Prose as a Covert AI Attack Vector
Check Point details PuzzleMask, a plain-prose technique that bypasses LLM gatekeeper policy checks, letting hidden payloads reach target models unreviewed.
Check Point Research describes PuzzleMask, a prompt-crafting technique that hides policy-violating payloads inside plain-English prose wrappers, bypassing quick LLM-based policy checks without emojis, Base64, or invisible formatting. The researchers tested 23 automated prompts against gatekeepers including GPT-4o-mini, GPT-OSS-Safeguard 20b, Claude 3 Haiku, and Llama Guard 3, and all were classified as safe despite policies that flagged the plain versions. When submitted to GPT-5 in thinking-high mode with a Python interpreter, the target model extracted and acted on the payload in over 90% of trials. The technique is not itself a jailbreak but can carry a jailbreak prompt as payload; mitigations include input paraphrasing, hardened gatekeeper policies, and output monitoring.
55
50
57
30
Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States
Mind2Dialogue simulates users' mental states to generate privileged supervision, boosting personalization and preference-following in Qwen, Llama, and OLMo assistants.
The Mind2Dialogue framework uses a psychology-guided simulator that preserves personal characteristics while updating user mental states through interaction, driving coherent conversations and an Oracle assistant's responses. Privileged distillation trains models on the Oracle's well-informed responses so they can assist users without direct access to mental states at deployment. Training on the full corpus improves every reported personalization metric over Qwen, Llama, and OLMo instruction-tuned baselines, including 26.6 to 40.9 percentage point gains in preference-following generation.
45
From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge
Interpretability study traces how Qwen, Llama, and Gemma route query information and internal knowledge across layers when answering questions.
Researchers used layerwise interventions on hidden states to separate query-routing signals from target knowledge in language models, testing Qwen, Llama, and Gemma on country-continent questions with varied answer types. A pair-conditioned request direction strengthens before interventions alter downstream knowledge, opening a causal window while answer-supporting content is still forming. Trajectories differ by model: Gemma shows a partially overlapping mid-layer routing profile, while Llama has no sustained routing-effect window under the same gates.
25
Training a 3.8B LLM to 0.384 CORE for $998 – Hugo Vergnes
Independent developer Hugo Vergnes trained a 3.8B-parameter Llama-style model to 0.384 CORE on 65B tokens for $998 in 43 hours on rented B200s.
Hugo Vergnes trained little-lm, a 3.848B-parameter decoder-only LLM, on 65.3B tokens in 43 hours for $998 using rented NVIDIA B200s, scoring 0.384 on the CORE benchmark and beating nanochat d32 (0.310) at similar cost. The Llama-style architecture uses RMSNorm, RoPE, GQA with 24 query and 8 KV heads, relu-squared MLPs, QK-norm, and ResFormer-style value embeddings that account for 19% of parameters. Key wins included the Muon optimizer for matrix parameters, a trapezoidal learning-rate schedule with linear cooldown, FP8 training plus vocabulary padding for roughly 33% throughput gains, and the ClimMix dataset over FineWeb-Edu. The project, inspired by Karpathy's nanochat, was built as a config-driven YAML framework for small LLM training.
35
Wazuh and AI For Enhanced SOC Workflows
Wazuh details AI-powered SOC workflows via its AI Analyst, self-hosted Llama 3 via Ollama, and Claude 3.5 Haiku integrations.
Wazuh outlines how AI can augment SOC analysts handling high alert volumes. The Wazuh AI Analyst on Wazuh Cloud uses Amazon Bedrock and Anthropic Claude to generate scheduled security posture reports. Self-hosted options include Llama 3 with Ollama, FAISS, and LangChain for privacy-sensitive threat hunting, plus an OpenSearch Assistant integration with Claude 3.5 Haiku. This is a vendor-contributed piece describing product capabilities rather than an incident or vulnerability.
25
30
50
30
60
LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Distress Prediction Across Heterogeneous Surveys
Schema-aware split learning uses LLaMA-3.2-3B-Instruct as shared semantic encoder to harmonize heterogeneous mental-health surveys while raw data stays local.
The paper proposes a schema-aware split learning framework where an LLM serializes heterogeneous mental health survey records into natural language and is fine-tuned via LoRA, partitioned across client and server. Clients keep raw survey responses local and run only a lightweight front-end while the resource-intensive backbone runs server-side. Using LLaMA-3.2-3B-Instruct, the framework attains an average ANLS of 0.708 with 2,000 training samples, beats federated learning in eight of nine settings, and cuts per-client computation by three orders of magnitude while generalizing to unseen datasets.
18
Decomposition-Guided Diffusion Language Models for Inertial Confinement Fusion Prediction
ICF-DLM, the first language-model-based inertial confinement fusion predictor, cuts peak-timing error from 11.6 to 9.2 steps versus LLaMA-3-8B.
Each National Ignition Facility shot costs roughly one million dollars, motivating accurate AI surrogates for predicting 512-step neutron-rate waveforms from laser pulses and target parameters. ICF-DLM combines physics-typed decomposition into yield, peak timing, and local waveform; bidirectional denoising that defers commitment to peak location; and a physics-driven PPO reward. On ICFBench (50,000 simulations plus 232 experimental shots) it outperforms a matched autoregressive LLaMA-3-8B, classical sequence models, and LLM-based time-series predictors.
16
50
42
30
55
30
Opaque recurrence, and other AI terms that you should probably know
TechCrunch updates its plain-English glossary defining common AI terms from AGI and agents to chain-of-thought reasoning.
TechCrunch maintains a regularly updated glossary of AI terminology, defining terms such as AGI, AI agents, API endpoints, chain of thought, coding agents, compute, deep learning, and diffusion. It highlights 'opaque recurrence', the reasoning technique in OpenAI's new Astra model that has drawn attention from AI safety researchers. The piece is an educational living document rather than new research or a product announcement.
18
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF — new model trending #3 on Hugging Face
ISTA-DASLab releases GSQ-RCO non-uniform GGUF quantizations of Qwen3.8-27B down to 2.5 bpw, with task-lossless IQ3_S matching BF16 benchmark scores.
ISTA-DASLab released GGUF quantizations of Qwen3.8-27B produced with GSQ (Gumbel-Softmax Quantization) and RCO (Riemannian Constrained Optimization), non-uniform methods that allocate per-tensor precision via gradient-based search under a total size budget. Four checkpoints range from 2.50 bpw (8.4 GB) to 3.50 bpw (11.8 GB), plus a BF16 vision projector (mmproj) enabling multimodal use. The recommended IQ3_S build is task-lossless, matching the BF16 base exactly on AIME25 (100.00) and LiveCodeBench v6 (85.71) at roughly one fifth of the BF16 size. Optional -mtp variants add a Multi-Token Prediction head for speculative decoding in llama.cpp.
44
45
30
30
50
30
60
30
45
60
55
30
42
30
50
30