{"id":537316,"url":"https://alion.io/job/interdigital-post-doctoral-researcher-hybrid-implicit-neural-representations-for-next-generation-learned-video-compression","title":"Post-doctoral researcher; Hybrid Implicit Neural Representations for Next-Generation Learned Video Compression","company":{"id":40047,"name":"InterDigital","domain":"interdigital.com","url":"https://alion.io/company/interdigital","size_band":"501-1000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Workday","truth_index":{"grade":"A","score":90,"open_postings":11,"ghost_share":0.091,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":70,"computed_at":"2026-11-05T05:54:30Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":"full_time","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"explicit","locations":["Rennes, France"],"countries":["FR"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":43000,"max_usd":94000,"period":"year","method":"role_country_seniority_unknown","sample_n":121},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"CNN","optional":false},{"name":"Computer Vision","optional":false},{"name":"Embeddings","optional":false},{"name":"Quantization","optional":false},{"name":"Wi-Fi","optional":false}],"status":"live","first_seen_at":"2026-07-14T00:00:00Z","employer_posted_date":"2026-07-14","last_verified_at":"2026-11-05T10:39:35Z","board_verified":true,"closed_at":null,"days_open":114,"trust":{"level":"ok","repost_count":0,"flags":["company_stale"],"days_open":114},"description":"JoinInterDigital'sVideo Lab to pioneer the next generation of energy-efficient AI for video. As a postdoctoral researcher, you will help shape technologies that reduce the environmental footprint of generative AI while contributing to international standards and publishingcutting-edgeresearch.\nAbout InterDigital\nInterDigital is a global research and development company focused primarily on wireless, video, artificial intelligence (“AI”), and related technologies. We design and develop foundational technologies that enable connected, immersive experiences in a broad range of communications and entertainment products and services. We license our innovations worldwide to companies providing such products and services, including makers of wireless communications devices, consumer electronics, IoT devices, cars and other motor vehicles, and providers of cloud-based services such as video streaming. As a leader in wireless technology, our engineers have designed and developed a wide range of innovations that are used in wireless products and networks, from the earliest digital cellular systems to 5G and today’s most advanced Wi-Fi technologies. We are also a leader in video processing and video encoding/decoding technology, with a significant AI research effort that intersects with both wireless and video technologies. Founded in 1972, InterDigital is listed on Nasdaq.\nInterDigital is a registered trademark of InterDigital, Inc.\nFor more information, visit: www.interdigital.com.\nBackground and Motivation\nThe continuous growth of video traffic generated by streaming platforms, immersive media, cloud gaming, autonomous systems, and machine vision is placing unprecedented pressure on communication and storage infrastructures. Although conventional video codecs such as H.266/VVC, AV1 and HEVC continue to improve coding efficiency through decades of algorithmic refinements, their block-based architecture is approaching diminishing returns. Their design relies on handcrafted signal processing modules-including prediction, transforms, quantization, in-loop filtering and entropy coding-that have been carefully optimized but remain fundamentally constrained by assumptions about natural image statistics.\nLearned Video Compression (LVC) has emerged during the past decade as a promising alternative. Instead of optimizing individual codec modules independently, learned codecs formulate compression as a global end-to-end optimization problem. Neural networks jointly learn the analysis transform, synthesis transform, entropy model and motion representation by minimizing a rate-distortion objectivewhere (D) measures reconstruction distortion while (R) estimates the coding rate through differentiable entropy models.\nRecent learned image and video codecs have demonstrated compression performances comparable to-or surpassing-the latest standard codecs for several operating points. More importantly, they provide a flexible framework in which every component can be jointly optimized for a target application.\nDespite these impressive advances, several important challenges remain before learned video codecs can become a practical replacement for conventional standards.\nFirst, current architectures remain computationally demanding. Deep convolutional encoders, decoders and optical-flow estimation networks require millions of parameters and substantial computational resources during both training and inference.\nSecond, entropy modeling remains one of the principal bottlenecks. State-of-the-art autoregressive models improve coding efficiency but introduce strong sequential dependencies that significantly reduce decoding parallelism.\nThird, current codecs still represent images and videos through discrete latent feature maps. While highly effective, these representations inherit many limitations of grid-based signals, including resolution dependence, interpolation artifacts and limited geometric adaptability.\nFinally, temporal redundancy is often modeled explicitly through optical flow or recurrent networks, both of which become increasingly expensive for long sequences or high-resolution content.\nThese limitations motivate the exploration of alternative signal representations capable of providing richer spatial and temporal modeling while maintaining efficient entropy coding.\nHybrid Implicit Neural Representations\nImplicit Neural Representations (INRs) have recently emerged as a fundamentally different paradigm for representing visual signals. Rather than storing an image or a video as discrete samples on a grid, an INR represents the signal as a continuous functionwhere the neural network maps spatial (or spatio-temporal) coordinates\nXΧ directly to signal valuesΥΥ.\nContinuous representations naturally provide:\narbitrary-resolution reconstruction,\n\nsmooth interpolation,\n\ncompact parameterization,\n\ngeometric continuity.\n\nHowever, pure coordinate-based INRs exhibit several limitations for compression. They often require relatively large neural networks, suffer from slow convergence, and struggle to reproduce highly textured regions without substantially increasing model complexity.\nHybrid Implicit Neural Representations (Hybrid INRs) have recently addressed these limitations by combining learned latent grids with coordinate-based neural decoders.\nInstead of relying solely on coordinates, the decoder receives both\nlocal latent features extracted from hierarchical latent grids,\n\ncontinuous spatial coordinates.\n\nThe latent grids capture high-frequency local structures while the implicit decoder reconstructs the continuous signal. Hierarchical latent resolutions allow coarse image structures to be represented at low spatial resolutions and fine details at higher resolutions.\nAmong recent examples, Cool-Chic[Ladune et al., 2003]and C3[Kim et al., 2024]havedemonstrated that hybrid INRs constitute an extremely competitive framework for learned image compression. Its hierarchical latent representation, lightweight implicit decoder and learned entropy model achieve state-of-the-art rate-distortion performance while requiring significantly fewer decoder parameters than conventional CNN-based architectures.\nThe advantages of hybrid INRs include:\ncontinuous image representation,\n\ncompact decoder architectures,\n\nscalable latent hierarchies,\n\ncompatibility with autoregressive entropy models,\n\nexcellent adaptation to image geometry.\n\nNevertheless, current hybrid INR methods remain largely restricted to still images. Extending this framework to video introduces new scientific questions regarding temporal representation, temporal prediction and entropy modeling[Leguay et al., 2024].\nExtending Hybrid INRs to Learned Video Compression\nThe central objective of this project is to develop a new generation of learned video codecs based on spatio-temporal hybrid implicit neural representations.Instead of treating each frame independently, the proposed framework will model an entire video sequence as a continuous function where the decoder jointly exploits spatial coordinates, temporal coordinates and hierarchical latent representations.The key challenge lies in introducing temporal redundancy into the latent hierarchy without sacrificing the compactness that makes hybrid INRs attractive.Several complementary research directions will be investigated.\nHierarchical Spatio-Temporal Latent Representation\nCurrent hybrid INR codecs organize latent grids across multiple spatial resolutions. This project proposes extending the representationto the temporal dimension.This could includetemporal latent pyramids,key-frame and inter-frame latent decomposition,multi-scale temporal feature grids,adaptive temporal resolutions depending on motion complexity…\n\nContinuous Temporal Prediction\n\nConventional learned video codecs typically estimate optical flow between successive frames.Hybrid INRs provide an opportunity to replace explicit motion estimation by continuous temporal modeling, such aslatent-space temporal prediction,learned temporal embeddings…\n\nHierarchical Context Modeling\n\nEntropy coding remains one of the largest contributors to coding performance.Inspired by recent advances in hierarchical latent modeling for image compression, previously decoded latent levels and previous temporal instants can provide rich contextual information for entropy prediction.\n\nLightweight Neural Architectures\n\nOne of the strengths of hybrid INRs is the possibility of using extremely compact decoders.The projectaims to continueinvestigatinglightweight architecturesaiming to reduceboth computational complexity and memory footprint while preserving coding performance.\n\nExpected Scientific Contributions\nThe proposed research will contribute to the development of a unified framework for learned video compression based onimplicit neural representation.\nExpected contributions include:\nnovel spatio-temporal hybrid INR architectures for video compression;\n\nlightweight decoder architectures suitable for practical deployment;\n\ncomprehensive rate-distortion-complexity evaluation against state-of-the-art learned video codecs and conventional standards such as VVC.\n\n Impact\nThis project addresses several major challenges facing next-generation multimedia compression: coding efficiency, computational complexity, scalability and representation flexibility. By extending hybrid implicit neural representations from images to videos, it seeks to establish a new paradigm in which spatial and temporal information are jointly modeled through continuous neural functions and hierarchical latent representations.\nSuch a framework has the potential to bridge the gap between neural signal representations and practical video coding systems, contributing both to the theoretical understanding of continuous neural compression and to the development of future AI-native video codecs suitable for real-world deployment.\nBibliography\n[Kim et al., 2024]Kim, Hyunjik, et al.\"C3: High-performance and low-complexity neural compression from a single image or video.\" Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024.\n[Ladune et al., 2003]Ladune, Théo, et al.\"Cool-chic: Coordinate-based low complexity hierarchical image codec.\" Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023.\n[Leguay et al., 2024]Leguay, Thomas, et al. \"Cool-chic video: Learned video coding with 800 parameters.\" 2024 Data compression conference (DCC). IEEE, 2024.\nLocation: Rennes, France\nInterDigital is an equal employment opportunity employer. InterDigital will not engage in or tolerate unlawful discrimination with regard to any employment decision, policy or practice based on a person’s sex, gender, pregnancy (including childbirth, breastfeeding and related medical conditions), age, race, color, religion, creed, national origin, ancestry, citizenship, military status, veteran status, mental or physical disability, medical condition, genetic information, sexual orientation, gender identity or expression, or any other factor protected by applicable federal, state or local law. This policy applies to all terms and conditions of employment, including, but not limited to, recruiting, hiring, compensation, benefits, training, assignments, evaluations, coaching, promotion, discipline, discharge and layoff.","description_format":"text","description_chars":11322,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"phd","optional":false},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"France","iso":"FR","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["RF & Wireless Hardware","Mobile Networks"],"lifecycle":[{"event":"open","at":"2026-09-08T07:50:42Z"}],"visa":[],"liveness":{"score":21,"band":"cold","label":"Long shot","p_open":1,"p_active":0.582,"p_room":0.36,"age_days":114,"expected_fill_days":70,"reasons":["conf:8","win:tail","crowd:"],"computed_at":"2026-11-05T05:54:30Z"},"pay":null,"html_url":"https://alion.io/job/interdigital-post-doctoral-researcher-hybrid-implicit-neural-representations-for-next-generation-learned-video-compression","json_url":"https://alion.io/job/interdigital-post-doctoral-researcher-hybrid-implicit-neural-representations-for-next-generation-learned-video-compression.json","meta":{"generated_at":"2026-11-05T11:18:27Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":14488,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-06T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":40047},"rest":"https://alion.io/mcp/rest/get_company?id=40047"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Finterdigital-post-doctoral-researcher-hybrid-implicit-neural-representations-for-next-generation-learned-video-compression"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Finterdigital-post-doctoral-researcher-hybrid-implicit-neural-representations-for-next-generation-learned-video-compression"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Finterdigital-post-doctoral-researcher-hybrid-implicit-neural-representations-for-next-generation-learned-video-compression"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/interdigital-post-doctoral-researcher-hybrid-implicit-neural-representations-for-next-generation-learned-video-compression\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Finterdigital-post-doctoral-researcher-hybrid-implicit-neural-representations-for-next-generation-learned-video-compression"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":537316}},{"tool":"search_jobs","arguments":{"company":"interdigital.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":537316},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}