Recent advances in AI have revolutionized speech processing, yet effective speech understanding requires discerning not just what is said, but how it is said. Speech Sentiment Analysis plays a critical role in decoding these paralinguistic cues for diverse real-world applications such as recruitment and customer service. However, existing Speech Sentiment Analysis research faces two primary limitations. First, dominant approaches rely on text-centric pipelines that cascade Automatic Speech Recognition with text analysis. This process inevitably discards essential acoustic features like prosody and tone, failing to capture attitudinal meanings in acoustically ambiguous utterances. Second, current benchmarks suffer from a mismatch in label granularity, prioritizing basic emotions (e.g., happy, sad) over the nuanced interpersonal stances (e.g., confident, impatient) necessary for social sensitivity. To address these limitations, we propose a novel dataset, SpeechSense, for fine-grained speech sentiment analysis. Specifically, we define a specialized 8-class taxonomy of interpersonal stances detectable primarily through prosodic cues beyond lexical content alone. We then construct a curated dataset based on this taxonomy, built from high-fidelity speech synthesis and rigorous human validation. Comprehensive experiments across multi-modal LLMs, text-only LLMs, and speech encoders demonstrate that models with acoustic access consistently outperform text-only baselines. These results empirically validate the primacy of acoustic cues in detecting subtle speaker attitudes, highlighting the necessity of SpeechSense. Dataset and supplementary materials are available at https://github.com/Sher13cked/SpeechSense.
A language model's output does not by itself provide verifiable evidence about the internal computation that produced it. We study computational provenance: whether generated text can carry detectable evidence of which causally relevant internal state occurred. We test a bounded form of this idea in two controlled architectures: a modular feed-forward neural network and a transformer-based model. Both architectures are trained on the same arithmetic task with a mandatory pathway through two discrete intermediate states, allowing different internal paths to produce the same answer. We deliberately switch between these paths, authenticate the state actually used, and let that verified state determine a subtle statistical pattern in the generated text that can later be detected. The feed-forward and transformer systems each passed all 128 matched pairs in both their public and separately sealed protected end-to-end evaluations, with the detector recovering the signal associated with the authenticated internal state. The required causal computation also reproduced across five independently trained feed-forward models and three independently trained transformers. In a separate answer-only transformer experiment, our linear probes did not recover a naturally learned intermediate state. These results provide a controlled proof of concept that information about a verified, causally relevant internal state can be preserved in generated text even when the answer is unchanged.
Assine o Pro, sem anúncios
Faça upgrade para uma leitura sem interrupções e acesso prioritário a novas fontes.
New image-text-to-text model. Tags: gguf, abliterated, uncensored, huihui, qwen3, image-text-to-text, base_model:Qwen/Qwen3.8-27B, base_model:quantized:Qwen/Qwen3.8-27B
New image-text-to-text model. Tags: qwen3_5, image-text-to-text, abliterated, uncensored, huihui, qwen3, conversational, base_model:Qwen/Qwen3.8-27B
New image-text-to-text model. Tags: qwen3_5, image-text-to-text, abliterated, qwen3.8, uncensored, ai-red-team, red-teaming, fp8
New image-text-to-text model. Tags: qwen3_5, image-text-to-text, unsloth, GAIN Training, COLD-FUSION, finetune, conversational, base_model:Qwen/Qwen3.8-27B
New image-text-to-text model. Tags: gguf, image-text-to-text, base_model:Qwen/Qwen3.8-27B, base_model:quantized:Qwen/Qwen3.8-27B, license:apache-2.0, imatrix, conversational
New image-text-to-text model. Tags: qwen3_5, image-text-to-text, conversational, base_model:Qwen/Qwen3.8-27B, base_model:quantized:Qwen/Qwen3.8-27B, license:apache-2.0, fp8
New image-text-to-text model. Tags: lfm2_vl, image-text-to-text, liquid, lfm2.5, edge, conversational, custom_code, ar
New image-text-to-text model. Tags: gguf, unsloth, meta, image-text-to-text, arxiv:2504.13181, arxiv:2602.06036, base_model:meta-models/Muse-Glimmer-30B, base_model:quantized:meta-models/Muse-Glimmer-30B
New image-text-to-text model. Tags: muse_glimmer, image-text-to-text, conversational, arxiv:2504.13181, arxiv:2602.06036, license:apache-2.0, eval-results
New image-text-to-text model. Tags: qwen3_5, image-text-to-text, conversational, license:apache-2.0, eval-results, deploy:azure
New image-text-to-video model. Tags: minimax-h3, diffusers, text-to-video, image-to-video, image-text-to-video, video-to-video, text-to-audio-video, image-to-audio-video
New image-text-to-text model. Tags: kimi_k3, feature-extraction, compressed-tensors, conversational, image-text-to-text, custom_code, license:other, eval-results
Overview of adaptive parallel reasoning. What if a reasoning model could decide for itself when to decompose and parallelize independent subtasks, how many concurrent threads to spawn, and how to coordinate them based on the problem at hand? We provide a detailed analysis of recent progress in the field of parallel reasoning, especially Adaptive Parallel Reasoning. Disclosure: this post is…
New image-text-to-text model. Tags: gguf, uncensored, qwen3.6, vision, multimodal, image-text-to-text, en, zh
Current 3D generation methods lack explicit local control: geometric adherence is often defined by a global control strength, and appearance cannot be specified locally. We present SpaceFlow, a training-free pipeline for locally controllable 3D generation from text descriptions and a collection of geometric primitives. Each primitive serves as a proxy for an object part and is assigned a local control level, enabling users to specify whether regions should strictly follow the input shape or allow generative completion. During structure generation, we enforce these spatial constraints within the generative flow process. For appearance synthesis, the generated structure is segmented and matched to the primitives. Each generated part is conditioned only on its assigned text or image cue, thereby limiting cross-part leakage. Regional geometry metrics demonstrate that SpaceFlow preserves the specified geometry in high-control regions and enables plausible shape variation in low-control areas. A user study further indicates that the resulting balance between geometric fidelity and generative freedom remains competitive in overall quality. When evaluating appearance on fixed geometry, text-conditioned routing achieves state-of-the-art prompt faithfulness and color/material accuracy. Qualitative results additionally show localized routing of image cues. The project page is available at SpaceFlow3D.github.io.
Industrial risk-control systems typically rely on structured-data models for efficient prediction, yet substantial valuable information remains embedded in unstructured long text. Extracting this information through manual feature engineering is labor-intensive, while requiring a large language model (LLM) to process every real-time input may not meet practical deployment requirements. To address this challenge, we propose LLM-BlockFE, an LLM-guided offline feature construction framework that converts long text into executable feature programs, thereby avoiding LLM calls during online inference. LLM-BlockFE constructs feature programs by incrementally appending immutable code blocks and evaluates candidate features using a downstream model. To address the tendency of conventional greedy search to become trapped in suboptimal solutions, our method introduces a block-level rollback mechanism based on depth-calibrated credit allocation and advances multiple independent search trajectories in an interleaved manner, reducing redundant exploration by sharing fixed descriptions of each trajectory's exploration direction. After the search, the resulting programs are frozen and deployed to extract structured features for downstream prediction models. Across two public and two private datasets, LLM-BlockFE achieves absolute AUC improvements of 0.0069 to 0.0358 over the strongest baseline on each dataset in the full-dataset comparison. Post-launch monitoring across five deployed financial risk-control applications shows absolute KS improvements of 0.02 to 1.56 percentage points over the existing manually designed strategy.
