drowzeys/DeepSeek-V4.1-Flash-Abliterated-Cybersecurity-Unleashed
New image-text-to-text model. Tags: deepseek, deepseek-v4.1, deepseek-v4.1-flash, abliterated, uncensored, cybersecurity, moe, fp8
en♥ 118
Buscar
Busca
868
LLMs as Feature Engineers for Text-and-Tabular Prediction
We introduce an iterative framework that automates the extraction of interpretable, schema-bound categorical features from unstructured text for tabular prediction models. To navigate the feature space, a generator LLM proposes semantic definitions, a separate extractor LLM materializes the features, and a downstream tabular model evaluates their predictive performance. We optimize this search by translating explicit model errors, such as AUC ranking inversions, into natural-language feedback, steering the LLM to resolve specific predictive failures. Evaluated across three public datasets, this error-driven loop accelerates feature discovery by up to 3compared to unguided search. Empirically, the generated features demonstrate strong multi-view complementarity, strictly outperforming any subset when combined with TF-IDF and dense embeddings. Finally, the framework guarantees instance-level interpretability: the discovered features dominate SHAP importance rankings and provide a fully transparent, semantic audit trail for every prediction.
en
AlexWortega/openjev
New text-classification model. Tags: nli, cross-encoder, qwen3.5, reranker, text-classification, en, base_model:Qwen/Qwen3.5-4B, base_model:finetune:Qwen/Qwen3.5-4B
en♥ 100
Assine o Pro, sem anúncios
Faça upgrade para uma leitura sem interrupções e acesso prioritário a novas fontes.
Ver preçoscyjin-yl/Qwen3.8-27B-Uncensored-Cyber-agentic-imatrix-GGUF
New image-text-to-text model. Tags: gguf, imatrix, quantized, agentic, qwen3, llama.cpp, v100, uncensored
en♥ 123
Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure
Semantic cell annotation improves chunking interpretability for spreadsheets in LLM-driven RAG systems, aiding answer generation through enriched context rather than improved retrieval accuracy. We propose a novel framework of splitting any spreadsheet into interpretable chunks using cell role annotation. Our framework beats the state of the art, yet it faces a hard ceiling. Spreadsheets are fundamentally two-dimensional unstructured data with continuous relationships and infinite potential cell roles. Because classification models are restricted to finite, pre-defined classes, they cannot perfectly capture this structural nuance, even with human-level annotation. We show that addressing the spreadsheet-to-LLM bottleneck requires moving beyond discrete cell classification. Instead, the field must develop dimensionality-reduction techniques to directly flatten 2D unstructured spreadsheets into 1D unstructured text. Text chunks would be easier for downstream RAG to interpret and generate from.
en
XingChen-AGI/Xing4.0-29B-A4B
New text-generation model. Tags: xing4_0, text-generation, conversational, custom_code, arxiv:2512.24157, arxiv:2507.18013, license:apache-2.0
en♥ 118
Enhancing industrial safety AI with synthetic data on Amazon SageMaker AI
Learn how to build a synthetic data augmentation pipeline on Amazon SageMaker AI and Amazon Rekognition that generates photo-realistic, auto-labeled training images for industrial safety AI. This approach improved person detection by up to 160% without manual annotation or hazardous data collection near heavy machinery.
en
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF
New image-text-to-text model. Tags: gguf, gsq, rco, quantization, mixed-precision, ist-daslab, moe, multimodal
en♥ 97
harshatheg/Qwen-2.5-1B-RLCD
New text-generation model. Tags: mlx, structured-generation, parallel-decoding, constrained-decoding, apple-silicon, classification, json, text-generation
en♥ 97
Improving HCLS AI reasoning with open-source agent skills
AI agents on foundation models often misapply healthcare and life sciences decision frameworks, citing the right guideline but applying it incorrectly. This post shares 38 open-source agent skills across 11 HCLS domains that close this gap, with installation steps, three worked use cases, and a 410-prompt evaluation showing a 70-86% win rate.
en
nvidia/GLM-5.3-Flash-NVFP4
New image-text-to-text model. Tags: Model Optimizer, glm5_next, nvidia, ModelOpt, GLM-5, quantized, FP4, fp4
en♥ 90
audnai/penclaw-GLM-5.3-abliterated
New text-generation model. Tags: glm_moe_dsa, text-generation, abliterated, uncensored, warlock, audn, GLM-5.3, conversational
en♥ 98
TTM-Bench: A Framework for Text-to-Music System Performance Benchmarking
Text-to-music (TTM) systems are increasingly used to generate musical audio from natural-language descriptions. Robust evaluation is therefore essential, yet reliable performance comparison remains challenging. This difficulty stems from differences in system architecture, supported conditioning information, and access mode, as well as heterogeneous and fragmented metrics that cannot be applied uniformly across systems. To address these challenges, we introduce TTM-Bench, a framework that defines a common protocol for systematic, reproducible performance benchmarking of contemporary TTM systems. It evaluates performance along two dimensions: musical-content alignment, quantified by interpretable semantic, genre, and musical-descriptor agreement scores against a common musical specification and summarized by an aggregate score; and computational efficiency, characterized by generation latency and real-time factor, alongside resource use for local models and cost for hosted services. We demonstrate the framework through a preliminary comparative case study, illustrating the complementary evidence captured by these dimensions. The results show that higher musical-content alignment does not systematically coincide with lower computational demands, highlighting the importance of assessing TTM performance through distinct, interpretable measures rather than a reductive overall indicator.
en
VoiceTrace: A Benchmark and Retrieval Framework for Who-Said-What Speech Retrieval
Speech retrieval has become increasingly important as spoken content continues to grow across meetings, lectures, podcasts, and videos. Existing benchmarks and models have advanced semantic search over spoken content, but largely focus on what is said while overlooking who says it. In many real-world scenarios, however, users need to retrieve speech based jointly on semantic content and a target speaker, where the speaker may be specified naturally through a reference speech utterance rather than a predefined identity. To address this gap, we introduce VoiceTrace-Bench, a benchmark for hybrid speech retrieval in which each query combines text specifying what to retrieve with reference speech specifying who to retrieve. This setting requires models to integrate complementary semantic and speaker information directly from heterogeneous query inputs. Motivated by the joint audio-text modeling capabilities of audio-language models (ALMs), we develop VoiceTrace, a two-stage retrieval framework consisting of VoiceTrace-Emb, an embedding model that learns unified representations for efficient large-scale retrieval, and VoiceTrace-Reranker, a reranking model that jointly examines each query--candidate pair for fine-grained relevance estimation. Experiments show that VoiceTrace achieves state-of-the-art performance on established semantic speech retrieval benchmarks, while substantially outperforming cascade-based approaches on VoiceTrace-Bench, demonstrating its effectiveness for both conventional semantic retrieval and the new hybrid retrieval setting.
en
Nameless Tokenization: A Lossless Tokenizer-Level Defense Against Control-Token Forgery in Open-Weight LLMs
Open-weight language models publish the strings their chat templates use to mark turns, roles and tool results, which the tokenizer maps back to the reserved identifiers the model obeys. Anyone who controls text in a prompt can therefore write a turn boundary indistinguishable from one the serving stack wrote. We audit 256 deployed chat tokenizers. All are forgeable, and the flag usually recommended as a fix leaves 56.6% forgeable because it misses the tool and reasoning markers agent systems rely on. We propose nameless tokenization, which leaves the control entries with a reserved identifier and no surface string, so the content encoder cannot emit one and message content reaches the model unaltered. Across five tokenizer families it reproduces the standard token stream exactly on attack-free data and lifts accuracy on a probe of delimiter-bearing text from 8.5% to 59.9%, where sanitizers lose it. Separating a delimiter's appearance from its identifier shows the identifier matters little against a bare task instruction, but carries most of a forged tool result and most of any forged turn once the system message tells the model to treat user content as data.
en
Qwen/Qwen2.5-7B-Instruct
New text-generation model. Tags: qwen2, text-generation, chat, conversational, en, arxiv:2309.00071, arxiv:2407.10671, base_model:Qwen/Qwen2.5-7B
en♥ 2107
moonshotai/Kimi-K2-Instruct
New text-generation model. Tags: kimi_k2, text-generation, conversational, custom_code, doi:10.57967/hf/5976, license:other, eval-results, fp8
en♥ 2810
Qwen/Qwen3-8B
New text-generation model. Tags: qwen3, text-generation, conversational, arxiv:2309.00071, arxiv:2505.09388, base_model:Qwen/Qwen3-8B-Base, base_model:finetune:Qwen/Qwen3-8B-Base, license:apache-2.0
en♥ 1754