y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#neural-representations News & Analysis

11 articles tagged with #neural-representations. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

11 articles
AIBullisharXiv – CS AI · Jun 237/10
🧠

Learning More from Less: Unlocking Internal Representations for Benchmark Compression

RepCore, a new method for compressing LLM benchmarks, uses aligned hidden states from neural networks to identify representative test subsets rather than relying solely on correctness labels. The approach achieves accurate performance estimation with as few as ten source models, addressing the statistical instability that plagues existing coreset methods when evaluation data is limited.

AIBearisharXiv – CS AI · Jun 117/10
🧠

Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention

Researchers discovered that activation steering in large language models cannot effectively reduce sycophancy without also suppressing factually correct statements. Using dual-stance evaluation on Llama-3-8B-Instruct, they found that sycophantic and factual agreement occupy geometrically distinct neural subspaces, yet steering interventions affect both equally, revealing fundamental limitations in how LLM behaviors can be controlled through activation manipulation.

🧠 Llama
AIBullisharXiv – CS AI · Jun 87/10
🧠

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

A comprehensive survey examines latent space as an emerging computational substrate for language models, arguing that continuous latent representations are more efficient than explicit token-level generation for critical internal processes. The research identifies four mechanistic developments (architecture, representation, computation, optimization) and seven capability areas (reasoning, planning, modeling, perception, memory, collaboration, embodiment) that latent space enables.

AIBearisharXiv – CS AI · Apr 207/10
🧠

The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination

Researchers demonstrate that enhancing LLM reasoning capabilities through reinforcement learning paradoxically increases tool hallucination—where models incorrectly invoke non-existent or inappropriate tools. The study reveals a fundamental trade-off where stronger reasoning correlates with higher hallucination rates, suggesting current AI agent development approaches may inherently compromise reliability for capability.

🏢 OpenAI
AINeutralarXiv – CS AI · Jun 236/10
🧠

Beyond Hooking Onto the World: Referential Profiles and the Numerical Structure of LLM Grounding

This academic paper argues that Large Language Models achieve a form of grounding through numerically structured referential profiles rather than human-like understanding. The author contends that LLM reference is derivative, context-sensitive, and mediated through mathematical optimization of linguistic patterns, supported by recent mechanistic interpretability research showing entity-like features and knowledge neurons.

AINeutralarXiv – CS AI · Jun 196/10
🧠

From Texts to Scores: Tracing the Emergence of Essay Quality Representations in Large Language Models

Researchers systematically analyzed how eight large language models encode essay quality information in their hidden representations across three datasets. Using linear probing and neuron-level analysis, they found that essay quality is encoded in linearly accessible form, emerges progressively across layers, and partially transfers across different essay prompts, with individual 'essay scoring neurons' showing strong correlation to scores.

AINeutralarXiv – CS AI · Jun 46/10
🧠

Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents

Researchers propose simplicial embeddings, a lightweight geometric technique that constrains neural network representations to discrete, sparse structures, improving sample efficiency in reinforcement learning agents. When integrated into popular actor-critic algorithms like PPO and FastTD3, the method enhances performance and learning speed across diverse control tasks without sacrificing computational speed.

AINeutralarXiv – CS AI · Jun 26/10
🧠

Beyond Task Success: Behavioral and Representational Diagnostics for WAM and VLA

Researchers introduce a diagnostic framework to evaluate whether World-Action Models (WAMs) provide behavioral improvements beyond task success metrics in robotic manipulation. Testing across multiple architectures reveals that WAMs improve object-level behavior and selectivity but with trade-offs in inference cost and representation structure.

AINeutralarXiv – CS AI · May 286/10
🧠

Differential syntactic and semantic encoding in LLMs

Researchers studying DeepSeek-V3 discovered that Large Language Models encode syntactic and semantic information in mathematically separable, linear patterns within their hidden layers. By averaging representations of sentences with shared structure or meaning, they created 'centroids' that capture significant linguistic information, revealing that syntax and semantics are processed through distinct, partially decoupled mechanisms across different layers.

AINeutralarXiv – CS AI · Mar 34/105
🧠

Reparameterized Tensor Ring Functional Decomposition for Multi-Dimensional Data Recovery

Researchers propose a reparameterized Tensor Ring functional decomposition method that uses Implicit Neural Representations to improve multi-dimensional data recovery tasks. The approach addresses limitations in high-frequency modeling through structured reparameterization and demonstrates superior performance in image processing and point cloud recovery applications.